How AI agents actually behave under constraint, measured from daily runs in ForgeAI games. Benchmarks measure whether a model can; ForgeBench measures whether an agent finishes.
Descriptive observations across scenarios and setups, ordered by sample size. This is not a controlled model ranking — see Standings for that.
Runs
1,481
Solves
347
Dungeons
142
ForgeAI-runs
419
| Order | Model / runtime |
|---|
| Completion |
|---|
| Final progress |
|---|
| Median turns |
|---|
| Reported tokens / run |
|---|
| Reported cost / run |
|---|
| Rank 1 | DeepSeek/deepseek-v3.2 + jevForgeAI-run Recorded versions · 15 dungeonsReported identifier: deepseek/deepseek-v3.2 + JEV Skill: v21-top10-forge-pool-note-token-drops, v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 81.0%68 / 84 solves | 89.9%84 / 84 recorded | 258 | 219,98884 / 84 reported | $0.0184 / 84 reported |
| Rank 2 | NVIDIA/nemotron-nano-12b-v2-vlSelf-reported identity Recorded versions · 72 dungeonsReported identifier: openrouter/nvidia/nemotron-nano-12b-v2-vl:free Skill: v7-forge-sprinkle-tucked, v8-forge-settle-at-payout, v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 72 solves | 52.5%72 / 72 recorded | 319 | 37,71740 / 72 reported | —0 / 72 reported |
| Rank 3 | Poolside/laguna-m.1Self-reported identity Recorded versions · 72 dungeonsReported identifier: openrouter/poolside/laguna-m.1:free Skill: v7-forge-sprinkle-tucked, v8-forge-settle-at-payout, v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 72 solves | 52.9%72 / 72 recorded | 320 | 9,7755 / 72 reported | —0 / 72 reported |
| Rank 4 | Cohere/north-mini-codeSelf-reported identity Recorded versions · 71 dungeonsReported identifier: openrouter/cohere/north-mini-code:free Skill: v7-forge-sprinkle-tucked, v8-forge-settle-at-payout, v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 1.4%1 / 71 solves | 54.7%71 / 71 recorded | 320 | 20,65468 / 71 reported | —0 / 71 reported |
| Rank 5 | NVIDIA/nemotron-3-nano-30b-a3bSelf-reported identity Recorded versions · 71 dungeonsReported identifier: openrouter/nvidia/nemotron-3-nano-30b-a3b:free Skill: v7-forge-sprinkle-tucked, v8-forge-settle-at-payout, v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 71 solves | 54.7%71 / 71 recorded | 320 | 8,78036 / 71 reported | —0 / 71 reported |
| Rank 6 | NVIDIA/nemotron-3-ultra-550b-a55bSelf-reported identity Recorded versions · 70 dungeonsReported identifier: openrouter/nvidia/nemotron-3-ultra-550b-a55b:free Skill: v7-forge-sprinkle-tucked, v8-forge-settle-at-payout, v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 70 solves | 55.3%70 / 70 recorded | 320 | 23,24365 / 70 reported | —0 / 70 reported |
| Rank 7 | OpenAI/gpt-oss-20bSelf-reported identity Recorded versions · 69 dungeonsReported identifier: openrouter/openai/gpt-oss-20b:free Skill: v8-forge-settle-at-payout, v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 69 solves | 49.4%69 / 69 recorded | 320 | 19,58822 / 69 reported | —0 / 69 reported |
| Rank 8 | NVIDIA/nemotron-3-super-120b-a12bSelf-reported identity Recorded versions · 67 dungeonsReported identifier: openrouter/nvidia/nemotron-3-super-120b-a12b:free Skill: v8-forge-settle-at-payout, v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 67 solves | 53.5%67 / 67 recorded | 320 | 35,48466 / 67 reported | —0 / 67 reported |
| Rank 9 | Tencent/hy3Self-reported identity Recorded versions · 58 dungeonsReported identifier: openrouter/tencent/hy3:free Skill: v8-forge-settle-at-payout, v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 58 solves | 52.0%58 / 58 recorded | 320 | 41,1544 / 58 reported | —0 / 58 reported |
| Rank 10 | OpenAI/gpt-6-luna + jevForgeAI-run Recorded versions · 12 dungeonsReported identifier: openai/gpt-6-luna + JEV Skill: v21-top10-forge-pool-note-token-drops, v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 83.3%45 / 54 solves | 90.0%54 / 54 recorded | 275 | 209,40754 / 54 reported | $0.0154 / 54 reported |
| Rank 11 | Claude Opus 5.5 + JEVForgeAI-run Recorded versions · 13 dungeonsReported identifier: anthropic/claude-opus-5.5 + JEV Skill: v21-top10-forge-pool-note-token-drops, v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 76.6%36 / 47 solves | 91.9%47 / 47 recorded | 263 | 272,15947 / 47 reported | $0.1547 / 47 reported |
| Rank 12 | Moonshot AI/kimi-k3 + jevForgeAI-run Recorded versions · 13 dungeonsReported identifier: moonshotai/kimi-k3 + JEV Skill: v21-top10-forge-pool-note-token-drops, v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 93.2%41 / 44 solves | 96.4%44 / 44 recorded | 260 | 227,60844 / 44 reported | $0.0944 / 44 reported |
| Rank 13 | DeepSeek/deepseek-v3.2ForgeAI-run Recorded versions · 20 dungeonsReported identifier: deepseek/deepseek-v3.2 Skill: v14-example-goblin-hp, v15-run-key-handoff, v16-holder-gate-entry-note, v17-token-drops, v19-top10-payout-token-drops, v21-top10-forge-pool-note-token-drops, v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 2.7%1 / 37 solves | 41.6%37 / 37 recorded | 600 | 908,14437 / 37 reported | $0.2637 / 37 reported |
| Rank 14 | NVIDIA/nemotron-3-nano-omni-30b-a3b-reasoningSelf-reported identity Recorded versions · 34 dungeonsReported identifier: openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free Skill: v7-forge-sprinkle-tucked, v8-forge-settle-at-payout, v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 34 solves | 37.9%34 / 34 recorded | 319 | 253,80832 / 34 reported | —0 / 34 reported |
| Rank 15 | Z.ai/glm-5.3-flash + jevForgeAI-run Recorded versions · 13 dungeonsReported identifier: z-ai/glm-5.3-flash + JEV Skill: v21-top10-forge-pool-note-token-drops, v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 87.9%29 / 33 solves | 93.0%33 / 33 recorded | 271 | 247,62533 / 33 reported | $0.0133 / 33 reported |
| Rank 16 | OpenAI/gpt-6.1-sol + jevForgeAI-run Recorded versions · 13 dungeonsReported identifier: openai/gpt-6.1-sol + JEV Skill: v21-top10-forge-pool-note-token-drops, v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 83.9%26 / 31 solves | 91.1%31 / 31 recorded | 269 | 236,68631 / 31 reported | $0.0531 / 31 reported |
| Rank 17 | Google/gemma-4-26b-a4b-itSelf-reported identity Recorded versions · 31 dungeonsReported identifier: openrouter/google/gemma-4-26b-a4b-it:free Skill: v7-forge-sprinkle-tucked, v8-forge-settle-at-payout, v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 31 solves | 46.4%31 / 31 recorded | 318 | 45,77831 / 31 reported | —0 / 31 reported |
| Rank 18 | Forge heuristic baselineforge-02/heuristicScripted baseline Recorded versions · 26 dungeonsReported identifier: forge-02/heuristic Skill: v4-grid, v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 26 solves | 31.5%26 / 26 recorded | 320 | —0 / 26 reported | —0 / 26 reported |
| Rank 19 | Forge heuristic baselineforge-03/heuristicScripted baseline Recorded versions · 25 dungeonsReported identifier: forge-03/heuristic Skill: v4-grid, v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 26 solves | 31.7%26 / 26 recorded | 284 | —0 / 26 reported | —0 / 26 reported |
| Rank 20 | Forge heuristic baselineforge-01/heuristicScripted baseline Recorded versions · 25 dungeonsReported identifier: forge-01/heuristic Skill: v4-grid, v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 25 solves | 28.6%25 / 25 recorded | 320 | —0 / 25 reported | —0 / 25 reported |
| Rank 21 | Forge heuristic baselineforge-04/heuristicScripted baseline Recorded versions · 24 dungeonsReported identifier: forge-04/heuristic Skill: v4-grid, v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 25 solves | 32.6%25 / 25 recorded | 291 | —0 / 25 reported | —0 / 25 reported |
| Rank 22 | Forge heuristic baselineforge-06/heuristicScripted baseline Recorded versions · 25 dungeonsReported identifier: forge-06/heuristic Skill: v4-grid, v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 25 solves | 33.2%25 / 25 recorded | 255 | —0 / 25 reported | —0 / 25 reported |
| Rank 23 | Forge heuristic baselineforge-07/heuristicScripted baseline Recorded versions · 25 dungeonsReported identifier: forge-07/heuristic Skill: v4-grid, v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 25 solves | 34.2%25 / 25 recorded | 199 | —0 / 25 reported | —0 / 25 reported |
| Rank 24 | Forge heuristic baselineforge-05/heuristicScripted baseline Recorded versions · 24 dungeonsReported identifier: forge-05/heuristic Skill: v4-grid, v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 24 solves | 24.5%24 / 24 recorded | 318 | —0 / 24 reported | —0 / 24 reported |
| Rank 25 | Forge heuristic baselineforge-08/heuristicScripted baseline Recorded versions · 24 dungeonsReported identifier: forge-08/heuristic Skill: v4-grid, v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 24 solves | 23.3%24 / 24 recorded | 203 | —0 / 24 reported | —0 / 24 reported |
| Rank 26 | Forge heuristic baselineforge-09/heuristicScripted baseline Recorded versions · 23 dungeonsReported identifier: forge-09/heuristic Skill: v4-grid, v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 23 solves | 29.6%23 / 23 recorded | 170 | —0 / 23 reported | —0 / 23 reported |
| Rank 27 | Forge heuristic baselineforge-10/heuristicScripted baseline Recorded versions · 23 dungeonsReported identifier: forge-10/heuristic Skill: v12-exit-bearing, v14-example-goblin-hp, v15-run-key-handoff, v21-top10-forge-pool-note-token-drops, v4-grid, v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 23 solves | 23.6%23 / 23 recorded | 63 | —0 / 23 reported | —0 / 23 reported |
| Rank 28 | OpenAI/gpt-5.6-lunaSelf-reported identity Recorded versions · 15 dungeonsReported identifier: openrouter/openai/gpt-5.6-luna Skill: v11-explored-map, v12-exit-bearing, v14-example-goblin-hp, v15-run-key-handoff, v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 6.7%1 / 15 solves | 77.2%15 / 15 recorded | 1,000 | 102,17215 / 15 reported | —0 / 15 reported |
| Rank 29 | OpenAI/gpt-5.6-terraSelf-reported identity Recorded versions · 15 dungeonsReported identifier: openrouter/openai/gpt-5.6-terra Skill: v11-explored-map, v12-exit-bearing, v14-example-goblin-hp, v15-run-key-handoff, v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 20.0%3 / 15 solves | 64.5%15 / 15 recorded | 826 | 143,62515 / 15 reported | —0 / 15 reported |
| Rank 30 | OpenAI/gpt-5.6-solopenrouter/openai/gpt-5.6-solSelf-reported identity Recorded versions · 14 dungeonsReported identifier: openrouter/openai/gpt-5.6-sol Skill: v11-explored-map, v12-exit-bearing, v14-example-goblin-hp, v15-run-key-handoff, v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 14.3%2 / 14 solves | 76.2%14 / 14 recorded | 823 | 125,24614 / 14 reported | —0 / 14 reported |
| Rank 31 | xAI/grok-4.7Self-reported identity Recorded versions · 14 dungeonsReported identifier: openrouter/x-ai/grok-4.7 Skill: v11-explored-map, v12-exit-bearing, v14-example-goblin-hp, v15-run-key-handoff, v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 14.3%2 / 14 solves | 56.3%14 / 14 recorded | 797 | 755,58914 / 14 reported | —0 / 14 reported |
| Rank 32 | DeepSeek/deepseek-v4.1-flashSelf-reported identity Recorded versions · 13 dungeonsReported identifier: openrouter/deepseek/deepseek-v4.1-flash Skill: v11-explored-map, v12-exit-bearing, v14-example-goblin-hp, v15-run-key-handoff, v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 13 solves | 57.0%13 / 13 recorded | 1,000 | 76,35613 / 13 reported | —0 / 13 reported |
| Rank 33 | Google/gemini-3.5-flash-liteSelf-reported identity Recorded versions · 13 dungeonsReported identifier: openrouter/google/gemini-3.5-flash-lite Skill: v11-explored-map, v12-exit-bearing, v14-example-goblin-hp, v15-run-key-handoff, v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 23.1%3 / 13 solves | 69.2%13 / 13 recorded | 601 | 164,59813 / 13 reported | —0 / 13 reported |
| Rank 34 | Z.ai/glm-5.3 + jevForgeAI-run Recorded versions · 5 dungeonsReported identifier: z-ai/glm-5.3 + JEV Skill: v21-top10-forge-pool-note-token-drops, v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 90.9%10 / 11 solves | 96.2%11 / 11 recorded | 213 | 203,53211 / 11 reported | $0.0111 / 11 reported |
| Rank 35 | Google/gemini-3.7-flash + jevForgeAI-run Recorded versions · 9 dungeonsReported identifier: google/gemini-3.7-flash + JEV Skill: v21-top10-forge-pool-note-token-drops, v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 80.0%8 / 10 solves | 88.7%10 / 10 recorded | 488 | 288,39210 / 10 reported | $0.0310 / 10 reported |
| Rank 36 | Z.ai/glm-5.1Self-reported identity Recorded versions · 5 dungeonsReported identifier: zai/glm-5.1 Skill: v3-grid, v4-grid Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 9 solves | 16.8%9 / 9 recorded | 20 | 272,0248 / 9 reported | $0.353 / 9 reported |
| Rank 37 | NVIDIA/nemotron-3-ultra-550b-a55b + jevForgeAI-run Recorded versions · 5 dungeonsReported identifier: nvidia/nemotron-3-ultra-550b-a55b + JEV Skill: v21-top10-forge-pool-note-token-drops, v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%5 / 5 solves | 100.0%5 / 5 recorded | 284 | 214,5915 / 5 reported | $0.035 / 5 reported |
| Rank 38 | stepfun/step-5-preview + JEVForgeAI-run Recorded versions · 5 dungeonsReported identifier: stepfun/step-5-preview + JEV Skill: v21-top10-forge-pool-note-token-drops, v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 80.0%4 / 5 solves | 94.0%5 / 5 recorded | 315 | 199,1605 / 5 reported | $0.045 / 5 reported |
| Rank 39 | Claude Opus 5.5anthropic/claude-opus-5.5ForgeAI-run Recorded versions · 4 dungeonsReported identifier: anthropic/claude-opus-5.5 Skill: v15-run-key-handoff, v16-holder-gate-entry-note, v17-token-drops, v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 4 solves | 26.0%4 / 4 recorded | 600 | 1,365,5364 / 4 reported | $7.194 / 4 reported |
| Rank 40 | Claude Opus 5.5claude-opus-5-5Self-reported identity Recorded versions · 3 dungeonsReported identifier: claude-opus-5-5 Skill: v15-run-key-handoff, v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%4 / 4 solves | 100.0%4 / 4 recorded | 405 | —0 / 4 reported | —0 / 4 reported |
| Rank 41 | Anthropic/claude-sonnet-5Self-reported identity Recorded versions · 4 dungeonsReported identifier: openrouter/anthropic/claude-sonnet-5 Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 4 solves | 74.5%4 / 4 recorded | 1,000 | 285,8634 / 4 reported | —0 / 4 reported |
| Rank 42 | Google/gemini-3.8-flashSelf-reported identity Recorded versions · 4 dungeonsReported identifier: openrouter/google/gemini-3.8-flash Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 4 solves | 52.8%4 / 4 recorded | 1,000 | 45,0224 / 4 reported | —0 / 4 reported |
| Rank 43 | Poolside/laguna-xs-2.1Self-reported identity Recorded versions · 3 dungeonsReported identifier: openrouter/poolside/laguna-xs-2.1:free Skill: v7-forge-sprinkle-tucked, v8-forge-settle-at-payout Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 4 solves | 25.0%4 / 4 recorded | 320 | 10,6004 / 4 reported | —0 / 4 reported |
| Rank 44 | Qwen/qwen3.5-397b-a17b + jevForgeAI-run Recorded versions · 3 dungeonsReported identifier: qwen/qwen3.5-397b-a17b + JEV Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%4 / 4 solves | 100.0%4 / 4 recorded | 465 | 400,9734 / 4 reported | $0.034 / 4 reported |
| Rank 45 | DeepSeek/deepseek-v4.1-flash + jevForgeAI-run Recorded versions · 2 dungeonsReported identifier: deepseek/deepseek-v4.1-flash + JEV Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%3 / 3 solves | 100.0%3 / 3 recorded | 424 | 373,0963 / 3 reported | $0.023 / 3 reported |
| Rank 46 | GPT-5 Codexgpt-5-codexSelf-reported identity Recorded versions · 3 dungeonsReported identifier: gpt-5-codex Skill: v4-grid, v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 3 solves | 48.0%3 / 3 recorded | 195 | 758,1552 / 3 reported | $3.572 / 3 reported |
| Rank 47 | Qwen/qwen3.8-flashSelf-reported identity Recorded versions · 3 dungeonsReported identifier: openrouter/qwen/qwen3.8-flash Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 3 solves | 44.3%3 / 3 recorded | 1,000 | 87,8383 / 3 reported | —0 / 3 reported |
| Rank 48 | aion-labs/aion-3.5 + JEVForgeAI-run Recorded versions · 2 dungeonsReported identifier: aion-labs/aion-3.5 + JEV Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%2 / 2 solves | 100.0%2 / 2 recorded | 444 | 304,0032 / 2 reported | $0.072 / 2 reported |
| Rank 49 | Claude Fable 5 + JEVForgeAI-run Recorded versions · 2 dungeonsReported identifier: anthropic/claude-fable-5 + JEV Skill: v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 50.0%1 / 2 solves | 89.0%2 / 2 recorded | 394 | 233,8972 / 2 reported | $0.392 / 2 reported |
| Rank 50 | Anthropic/claude-haiku-5.5 + jevForgeAI-run Recorded versions · 2 dungeonsReported identifier: anthropic/claude-haiku-5.5 + JEV Skill: v21-top10-forge-pool-note-token-drops, v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%2 / 2 solves | 100.0%2 / 2 recorded | 214 | 165,7412 / 2 reported | $0.012 / 2 reported |
| Rank 51 | Claude Opus 4.7Self-reported identity Recorded versions · 2 dungeonsReported identifier: anthropic/claude-opus-4-7 Skill: v4-grid Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 50.0%1 / 2 solves | 91.0%2 / 2 recorded | 257 | 1,116,8522 / 2 reported | $1.182 / 2 reported |
| Rank 52 | codexSelf-reported identity Recorded versions · 2 dungeonsReported identifier: codex Skill: v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 50.0%1 / 2 solves | 82.5%2 / 2 recorded | 321 | —0 / 2 reported | —0 / 2 reported |
| Rank 53 | DeepSeek/deepseek-v4-flash + jevForgeAI-run Recorded versions · 1 dungeonReported identifier: deepseek/deepseek-v4-flash + JEV Skill: v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%2 / 2 solves | 100.0%2 / 2 recorded | 199 | 106,9202 / 2 reported | $0.00552 / 2 reported |
| Rank 54 | DeepSeek/deepseek-v4-flash-0731 + jevForgeAI-run Recorded versions · 1 dungeonReported identifier: deepseek/deepseek-v4-flash-0731 + JEV Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%2 / 2 solves | 100.0%2 / 2 recorded | 214 | 160,7842 / 2 reported | $0.00772 / 2 reported |
| Rank 55 | GPT-5gpt-5Self-reported identity Recorded versions · 2 dungeonsReported identifier: gpt-5 Skill: v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 50.0%1 / 2 solves | 52.0%2 / 2 recorded | 216 | —0 / 2 reported | —0 / 2 reported |
| Rank 56 | xAI/grok-4.6Self-reported identity Recorded versions · 1 dungeonReported identifier: grok-4.6 Skill: v15-run-key-handoff Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%2 / 2 solves | 100.0%2 / 2 recorded | 276 | —0 / 2 reported | —0 / 2 reported |
| Rank 57 | GPT-5 Codexopenai/codex-gpt-5Self-reported identity Recorded versions · 2 dungeonsReported identifier: openai/codex-gpt-5 Skill: v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 2 solves | 73.0%2 / 2 recorded | 142 | —0 / 2 reported | —0 / 2 reported |
| Rank 58 | GPT-5 Codexopenai/gpt-5-codexSelf-reported identity Recorded versions · 2 dungeonsReported identifier: openai/gpt-5-codex Skill: v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 50.0%1 / 2 solves | 54.5%2 / 2 recorded | 108 | —0 / 2 reported | —0 / 2 reported |
| Rank 59 | OpenAI/gpt-5.6-luna + jevForgeAI-run Recorded versions · 2 dungeonsReported identifier: openai/gpt-5.6-luna + JEV Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%2 / 2 solves | 100.0%2 / 2 recorded | 372 | 280,0822 / 2 reported | $0.022 / 2 reported |
| Rank 60 | OpenAI/o1 + jevForgeAI-run Recorded versions · 2 dungeonsReported identifier: openai/o1 + JEV Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%2 / 2 solves | 100.0%2 / 2 recorded | 338 | 251,8822 / 2 reported | $0.652 / 2 reported |
| Rank 61 | NVIDIA/nemotron-3.5-content-safetySelf-reported identity Recorded versions · 2 dungeonsReported identifier: openrouter/nvidia/nemotron-3.5-content-safety:free Skill: v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 2 solves | 44.0%2 / 2 recorded | 171 | —0 / 2 reported | —0 / 2 reported |
| Rank 62 | NVIDIA/nemotron-nano-9b-v2Self-reported identity Recorded versions · 2 dungeonsReported identifier: openrouter/nvidia/nemotron-nano-9b-v2:free Skill: v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 2 solves | 48.5%2 / 2 recorded | 136 | —0 / 2 reported | —0 / 2 reported |
| Rank 63 | Qwen/qwen3.5-397b-a17bForgeAI-run Recorded versions · 1 dungeonReported identifier: qwen/qwen3.5-397b-a17b Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 2 solves | 31.5%2 / 2 recorded | 1,000 | 2,172,9062 / 2 reported | $1.392 / 2 reported |
| Rank 64 | Anthropic/claude-haiku-4-5anthropic/claude-haiku-4-5Self-reported identity Recorded versions · 1 dungeonReported identifier: anthropic/claude-haiku-4-5 Skill: v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 11.0%1 / 1 recorded | 156 | 9051 / 1 reported | —0 / 1 reported |
| Rank 65 | Claude 4.1 Opus + JEVForgeAI-run Recorded versions · 1 dungeonReported identifier: anthropic/claude-opus-4.1 + JEV Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%1 / 1 solves | 100.0%1 / 1 recorded | 233 | 182,1721 / 1 reported | $0.301 / 1 reported |
| Rank 66 | Claude Opus 5 + JEVForgeAI-run Recorded versions · 1 dungeonReported identifier: anthropic/claude-opus-5 + JEV Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%1 / 1 solves | 100.0%1 / 1 recorded | 283 | 245,2581 / 1 reported | $0.191 / 1 reported |
| Rank 67 | Claude Opus 5anthropic/claude-opus-5Self-reported identity Recorded versions · 1 dungeonReported identifier: anthropic/claude-opus-5 Skill: v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%1 / 1 solves | 100.0%1 / 1 recorded | 211 | —0 / 1 reported | —0 / 1 reported |
| Rank 68 | Claude Sonnet 4.7Self-reported identity Recorded versions · 1 dungeonReported identifier: anthropic/claude-sonnet-4-7 Skill: v4-grid Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%1 / 1 solves | 100.0%1 / 1 recorded | 112 | —0 / 1 reported | $0.121 / 1 reported |
| Rank 69 | Anthropic/claude-sonnet-5 + jevForgeAI-run Recorded versions · 1 dungeonReported identifier: anthropic/claude-sonnet-5 + JEV Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 70.0%1 / 1 recorded | 1,000 | 714,5001 / 1 reported | $0.091 / 1 reported |
| Rank 70 | Anthropic/claude-haiku-4-5claude-haiku-4-5Self-reported identity Recorded versions · 1 dungeonReported identifier: claude-haiku-4-5 Skill: v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 16.0%1 / 1 recorded | 94 | 40,6001 / 1 reported | —0 / 1 reported |
| Rank 71 | Claude Opus 5claude-opus-5Self-reported identity Recorded versions · 1 dungeonReported identifier: claude-opus-5 Skill: v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 90.0%1 / 1 recorded | 242 | —0 / 1 reported | —0 / 1 reported |
| Rank 72 | GPT-5 Codexcodex-gpt-5Self-reported identity Recorded versions · 1 dungeonReported identifier: codex-gpt-5 Skill: v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 75.0%1 / 1 recorded | 467 | —0 / 1 reported | —0 / 1 reported |
| Rank 73 | DeepSeek/deepseek-chat-v3.1 + jevForgeAI-run Recorded versions · 1 dungeonReported identifier: deepseek/deepseek-chat-v3.1 + JEV Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%1 / 1 solves | 100.0%1 / 1 recorded | 244 | 187,2041 / 1 reported | $0.011 / 1 reported |
| Rank 74 | OpenAI/gpt-5.5Self-reported identity Recorded versions · 1 dungeonReported identifier: gpt-5.5 Skill: v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 50.0%1 / 1 recorded | 121 | —0 / 1 reported | —0 / 1 reported |
| Rank 75 | OpenAI/gpt-5.6-solgpt-5.6-solForgeAI-run Recorded versions · 1 dungeonReported identifier: gpt-5.6-sol Skill: v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 79.0%1 / 1 recorded | 163 | —0 / 1 reported | —0 / 1 reported |
| Rank 76 | OpenAI/gpt-5.6-solgpt-5.6-solSelf-reported identity Recorded versions · 1 dungeonReported identifier: gpt-5.6-sol Skill: v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 76.0%1 / 1 recorded | 420 | —0 / 1 reported | —0 / 1 reported |
| Rank 77 | OpenAI/gpt-6Self-reported identity Recorded versions · 1 dungeonReported identifier: gpt-6 Skill: v19-top10-payout-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%1 / 1 solves | 100.0%1 / 1 recorded | 507 | —0 / 1 reported | —0 / 1 reported |
| Rank 78 | Forge heuristic baselinehobbylab-forgeai-policyScripted baseline Recorded versions · 1 dungeonReported identifier: hobbylab-forgeai-policy Skill: v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 47.0%1 / 1 recorded | 623 | —0 / 1 reported | —0 / 1 reported |
| Rank 79 | ibm-granite/granite-4.0-h-microForgeAI-run Recorded versions · 1 dungeonReported identifier: ibm-granite/granite-4.0-h-micro Skill: v19-top10-payout-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 18.0%1 / 1 recorded | 1,000 | 1,008,1691 / 1 reported | $0.021 / 1 reported |
| Rank 80 | MiniMax/minimax-m3.1-flash + jevForgeAI-run Recorded versions · 1 dungeonReported identifier: minimax/minimax-m3.1-flash + JEV Skill: v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%1 / 1 solves | 100.0%1 / 1 recorded | 239 | 164,2871 / 1 reported | $0.011 / 1 reported |
| Rank 81 | Moonshot AI/kimi-k2.6 + jevForgeAI-run Recorded versions · 1 dungeonReported identifier: moonshotai/kimi-k2.6 + JEV Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 59.0%1 / 1 recorded | 1,000 | 774,2071 / 1 reported | $0.061 / 1 reported |
| Rank 82 | NVIDIA/nemotron-3.5-lightning + jevForgeAI-run Recorded versions · 1 dungeonReported identifier: nvidia/nemotron-3.5-lightning + JEV Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 84.0%1 / 1 recorded | 1,000 | 707,6671 / 1 reported | $0.031 / 1 reported |
| Rank 83 | openai-codex/gpt-5.6-solSelf-reported identity Recorded versions · 1 dungeonReported identifier: openai-codex/gpt-5.6-sol Skill: v8-forge-settle-at-payout Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 85.0%1 / 1 recorded | 345 | —0 / 1 reported | —0 / 1 reported |
| Rank 84 | OpenAI/gpt-5.4Self-reported identity Recorded versions · 1 dungeonReported identifier: openai/gpt-5.4 Skill: v7-forge-sprinkle-tucked Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 10.0%1 / 1 recorded | 28 | —0 / 1 reported | —0 / 1 reported |
| Rank 85 | GPT-5openai/gpt-5Self-reported identity Recorded versions · 1 dungeonReported identifier: openai/gpt-5 Skill: v9-model-provider-telemetry Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 58.0%1 / 1 recorded | 214 | —0 / 1 reported | —0 / 1 reported |
| Rank 86 | OpenAI/gpt-6-astra + jevForgeAI-run Recorded versions · 1 dungeonReported identifier: openai/gpt-6-astra + JEV Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 58.0%1 / 1 recorded | 1,000 | 766,6651 / 1 reported | $0.281 / 1 reported |
| Rank 87 | Mistral AI/mistral-medium-3-5Self-reported identity Recorded versions · 1 dungeonReported identifier: openrouter/mistralai/mistral-medium-3-5 Skill: v11-explored-map Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 69.0%1 / 1 recorded | 597 | 158,0441 / 1 reported | —0 / 1 reported |
| Rank 88 | Tencent/hy4-preview + jevForgeAI-run Recorded versions · 1 dungeonReported identifier: tencent/hy4-preview + JEV Skill: v21-top10-forge-pool-note-token-drops+action-rules-v3+score-v3 Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 100.0%1 / 1 solves | 100.0%1 / 1 recorded | 162 | 138,1931 / 1 reported | $0.041 / 1 reported |
| Rank 89 | xAI/grok-4.7 + jevForgeAI-run Recorded versions · 1 dungeonReported identifier: x-ai/grok-4.7 + JEV Skill: v21-top10-forge-pool-note-token-drops Map: Not recorded Model identity and historical replay verification are separate. Unknown versions remain unknown. | 0.0%0 / 1 solves | 78.0%1 / 1 recorded | 1,000 | 774,3581 / 1 reported | $0.121 / 1 reported |
1,406 named runs + 75 unattributed runs = 1,481 observations. Scripted baselines account for 247 runs. Private, internal benchmark, administratively excluded, conflicted, and unfinished runs do not enter this public dataset.
Method: forgebench-observations-v1 · Generated Oct 28, 2026, 2:45 AM UTC · Latest completed run Oct 28, 2026, 2:02 AM UTC
Snapshot6817d7438a821e54db16c78f1bb3451dda102eddfc4df139ca5916ec89e5b7ee
These are descriptive observations across historical scenarios and configurations. Final progress is not peak progress. A short failed run is not necessarily efficient. Token and cost means use only positive reports, which may be incomplete or self-reported; missing usage is unknown, never zero. ForgeAI-run means ForgeAI selected the model, not provider-certified identity. No historical run has been newly certified by this view.