Specification
most-agreed values
Context
32K
Max output
8K
Released
—
Knowledge cutoff
—
Retires
—
Open weights
—
Input
—
Output
—
Price
US dollars per million tokens · most-agreed
Input
$0.20
Output
$0.20
Quality
3 benchmarks · 1 source
Composite
2nd
percentile of 344 scored models
Rank
338 / 344
±0.06 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
—
one configuration only
reasoning1st1/4 bench
math1st2/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.3 ±0.3 | default | Epoch AI | 2026-08-30 |
| MATH level 5 | 3.6 ±0.3 | default · 2 runs | Epoch AI | 2025-01-27 |
| GPQA diamond | 14.2 ±1.0 | default · 2 runs | Epoch AI | 2025-01-27 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 2 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| fireworks_ai | $0.20 | $0.20 | — | — | 33K | 33K | — |
| snowflake | — | — | — | — | 32K | 8K | — |
More from Mistral
most-hosted first