B.O.B. Leaderboard
OpenAIreleased 9 Jul 2026
GPT-5.6 Sol Pro
#12 of 957 of 46 benchmarksnot enough data
82.0
B.O.B.
Category profile
- Real use (hard to game)2×72
- Reasoning & knowledge98
- Math85
- Coding90
- Agents & real work74
- Independent indexes—
Reality check
Needs results on at least 2 real-use tests before we can compare.
Price per 1M tokens (OpenRouter)
$4.00 in · $20.00 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 72 | |||
| SimpleBenchas gpt-5.6-sol_proxhigh | 71.7% | 72%of 30 | Epoch AI Benchmarking Hub |
| Reasoning & knowledge · Reasoning 98 | |||
| Chess Puzzlesas gpt-5.6-sol_promax | 68.0% | 98%of 73 | Epoch AI Benchmarking Hub |
| Math · Math 85 | |||
| FrontierMath Tier 4as gpt-5.6-sol_promax | 80.5% | 85%of 52 | Epoch AI Benchmarking Hub |
| Coding · Coding 90 | |||
| WeirdMLas gpt-5.6-sol_promax | 89.4% | 90%of 52 | Epoch AI Benchmarking Hub |
| Agents & real work · Agents 74 | |||
| LMCAas gpt-5.6-sol_promax | 59.2% | 92%of 67 | Epoch AI Benchmarking Hub |
| DTBenchas gpt-5.6-sol_promax | 96.0% | 81%of 67 | Epoch AI Benchmarking Hub |
| APEX-Agentsas gpt-5.6-sol_promax | 51.4% | 49%of 48 | Epoch AI Benchmarking Hub |