Benchmark menu

Model results

Mistral Medium 3.5

See how Mistral Medium 3.5 performed, which reasoning settings were tested, how often it produced a working player program, and what those runs cost.

Mistral Medium 3.5

Provider: Mistral

Rank
47
Status
Partial 2/3
Rank change
Baseline
Score
24.2
Last tested
2026-08-05
Settings tested
Balanced not supported

Why this result is partial: one or more bracket scores are missing; three distinct provider settings are not documented; one or more documented settings are untested or ineligible; generation-quality evidence is missing; generation quality is below the publication threshold. The rank uses the available reasoning-setting results.

Scores by reasoning setting

Available settings

NoneHigh

Checked on 2026-07-21 · Provider documentation

Scores from tested settings

Tested settingScoreResult statusDisplay group
None30.7Tested and includedBaseline
High17.8Tested and includedIntensive

How settings are grouped

  • Baseline: None — tested and included
  • Balanced: Not available for this model
  • Intensive: High — tested and included

Player program results

High: 22% / 22% / 56% · n 9None: 25% / 25% / 50% · n 8 Balanced not supportedMany programs failed

Generation cost

Average estimated cost
$0.12
Median estimated cost
$0.07
Estimated range
$0.02–$0.39
Cost data
16 combinations / 17 recorded runs
Observed total
$2.26
Price source
Provider-reported
Price list
Not recorded for this older data
Average output
15k tokens
Output range
1.5k–53k tokens
Samples
17

Estimated cost gives equal weight to each model, game, and reasoning-setting combination.

Test setup

  • Combines this model's tested reasoning settings
  • Uses the standard GameBench player-program prompt