B.O.B. Leaderboard
xAIreleased 29 May 2026
Grok Build 0.1
Not ranked yet3 of 46 benchmarksnot enough data
—
B.O.B.
Not ranked yet: B.O.B. needs at least 5 benchmarks across 3 categories. This model has 3 so far.
Category profile
- Real use (hard to game)2×—
- Reasoning & knowledge42
- Math—
- Coding45
- Agents & real work36
- Independent indexes—
Reality check
Needs results on at least 2 real-use tests before we can compare.
Price per 1M tokens (OpenRouter)
$1.00 in · $2.00 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 |
|---|---|---|---|
| Reasoning & knowledge · Reasoning 42 | |||
| CritPt (physics research)as grok-build-0.1 | 9.1% | 42%of 89 | Epoch AI Benchmarking Hub |
| Coding · Coding 45 | |||
| SciCodeas grok-build-0.1 | 50.2% | 45%of 86 | Epoch AI Benchmarking Hub |
| Agents & real work · Agents 36 | |||
| Game Boy Advance evalas grok-build-0.1 | 2.4% | 36%of 23 | Epoch AI Benchmarking Hub |