B.O.B. Leaderboard
OpenAIreleased 23 Apr 2026
GPT-5.5 Pro
#8 of 959 of 46 benchmarksnot enough data
86.6
B.O.B.
Category profile
- Real use (hard to game)2×90
- Reasoning & knowledge86
- Math85
- Coding—
- Agents & real work81
- Independent indexes89
Reality check
Needs results on at least 2 real-use tests before we can compare.
Price per 1M tokens (OpenRouter)
$30.00 in · $180.00 out
Cost per task on the AA index
—
Output speed (Artificial Analysis)
—
§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 90 | |||
| SimpleBenchas gpt-5.5-pro_unknown | 76.9% | 90%of 30 | Epoch AI Benchmarking Hub |
| Reasoning & knowledge · Reasoning 86 | |||
| Chess Puzzlesas gpt-5.5-pro_xhigh | 62.0% | 93%of 73 | Epoch AI Benchmarking Hub |
| CritPt (physics research)as gpt-5.5-pro_xhigh | 30.6% | 92%of 89 | Epoch AI Benchmarking Hub |
| ARC-AGI-2as gpt-5.5-pro_high | 84.6% | 73%of 44 | Epoch AI Benchmarking Hub |
| Math · Math 85 | |||
| FrontierMath Tiers 1-3as gpt-5.5-pro_xhigh | 87.7% | 88%of 60 | Epoch AI Benchmarking Hub |
| FrontierMath Tier 4as gpt-5.5-pro_xhigh | 78.0% | 81%of 52 | Epoch AI Benchmarking Hub |
| Agents & real work · Agents 81 | |||
| DTBenchas gpt-5.5-pro_xhigh | 96.0% | 81%of 67 | Epoch AI Benchmarking Hub |
| LMCAas gpt-5.5-pro_xhigh | 53.9% | 80%of 67 | Epoch AI Benchmarking Hub |
| Independent indexes · Indexes 89 | |||
| Epoch Capabilities Indexas GPT-5.5 Pro | 162.0 | 89%of 81 | Epoch AI |