B.O.B. Leaderboard
OpenAIreleased 29 Sep 2026
GPT-6.1 Sol
#5 of 9523 of 46 benchmarksConsistent
90.9
B.O.B.
Category profile
- Real use (hard to game)2×88
- Reasoning & knowledge97
- Math97
- Coding86
- Agents & real work88
- Independent indexes93
Reality check
Lab tests
92
Real use (6 tests)
88
Lab tests and real-use tests agree. It does 4 points better on the usual lab tests than on tests that are hard to train for.
What counts as real usePrice per 1M tokens (OpenRouter)
$2.00 in · $10.00 out
Cost per task on the AA index
$0.72
Output speed (Artificial Analysis)
55 tok/s
§Receipts
Every benchmark result
“Beats” = the share of tracked models this one beat on that test. The raw score is its best reported setting.
| Benchmark | Raw | Beats | Source |
|---|---|---|---|
| Real use (hard to game) · Real use 88 | |||
| LMArena Agent Arenaas GPT 6.1 Sol (Max) | 0.150 | 98%of 50 | LMArena (real agent sessions) |
| LMArena WebDevas gpt-6.1-sol-max | 1760 | 96%of 82 | LMArena (blind human votes) |
| LiveBench 2.0 (real-work suites)as gpt-6.1-sol | 84.5% | 90%of 39 | LiveBench / Abacus.AI |
| BridgeBench (overall)as GPT-6.1 Sol | 646 | 86%of 29 | BridgeMind |
| Vals Indexas openai/gpt-6.1-sol | 61.2% | 81%of 42 | Vals AI (private test sets) |
| LMArena Textas gpt-6.1-sol-max | 1484 | 79%of 80 | LMArena (blind human votes) |
| Reasoning & knowledge · Reasoning 97 | |||
| Mystery Game Puzzlesas gpt-6.1-sol_max | 80.0% | 98%of 57 | Epoch AI Benchmarking Hub |
| Chess Puzzlesas gpt-6.1-sol_max | 68.0% | 98%of 73 | Epoch AI Benchmarking Hub |
| ARC-AGI-2as gpt-6.1-sol_max | 94.2% | 98%of 44 | Epoch AI Benchmarking Hub |
| CritPt (physics research)as gpt-6.1-sol_max | 31.7% | 98%of 89 | Epoch AI Benchmarking Hub |
| SimpleQA Verifiedas gpt-6.1-sol_max | 73.9% | 96%of 57 | Epoch AI Benchmarking Hub |
| GPQA Diamondas gpt-6.1-sol_max | 95.4% | 95%of 70 | Epoch AI Benchmarking Hub |
| Math · Math 97 | |||
| FrontierMath Tier 4as gpt-6.1-sol_max | 100.0% | 100%of 52 | Epoch AI Benchmarking Hub |
| FrontierMath Tiers 1-3as gpt-6.1-sol_max | 93.7% | 99%of 60 | Epoch AI Benchmarking Hub |
| OTIS Mock AIMEas gpt-6.1-sol_max | 100.0% | 94%of 73 | Epoch AI Benchmarking Hub |
| ProofBenchas gpt-6.1-sol_unknown | 99.0% | 93%of 68 | Epoch AI Benchmarking Hub |
| Coding · Coding 86 | |||
| ALE-Benchas gpt-6.1-sol_max | 2743.8% | 99%of 71 | Epoch AI Benchmarking Hub |
| FrontierCodeas gpt-6.1-sol_medium | 50.2% | 86%of 45 | Epoch AI Benchmarking Hub |
| SciCodeas gpt-6.1-sol_high | 55.8% | 72%of 86 | Epoch AI Benchmarking Hub |
| Agents & real work · Agents 88 | |||
| GDP.pdfas gpt-6.1-sol_max | 35.0% | 100%of 37 | Epoch AI Benchmarking Hub |
| APEX-Agentsas gpt-6.1-sol_max | 60.0% | 77%of 48 | Epoch AI Benchmarking Hub |
| Independent indexes · Indexes 93 | |||
| Epoch Capabilities Indexas GPT-6.1 Sol | 166.3 | 98%of 81 | Epoch AI |
| Artificial Analysis Intelligence Indexas GPT-6.1 Sol (max) | 52 | 88%of 54 | Artificial Analysis |