B.O.B. Leaderboard
Mistral AIreleased 28 Apr 2026
Mistral Medium 3.5
Not ranked yet6 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 6 so far.
Category profile
- Real use (hard to game)2×9
- Reasoning & knowledge—
- Math—
- Coding—
- Agents & real work—
- Independent indexes8
Reality check
Needs results on at least 2 real-use tests before we can compare.
Price per 1M tokens (OpenRouter)
$1.50 in · $7.50 out
Cost per task on the AA index
$0.50
Output speed (Artificial Analysis)
166 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 9 | |||
| LMArena Textas mistral-medium-3.5 | 1427 | 15%of 80 | LMArena (blind human votes) |
| Kagi LLM Benchmarkas mistral-medium-3-5 | 41.4% | 10%of 22 | Kagi |
| LMArena WebDevas mistral-medium-3.5 | 1263 | 6%of 82 | LMArena (blind human votes) |
| LMArena Agent Arenaas Mistral Medium 3.5 | -0.110 | 4%of 50 | LMArena (real agent sessions) |
| Independent indexes · Indexes 8 | |||
| Artificial Analysis Intelligence Indexas Mistral Medium 3.5 | 14 | 15%of 54 | Artificial Analysis |
| Epoch Capabilities Indexas Mistral Medium 3.5 | 141.5 | 1%of 81 | Epoch AI |