DuelLabGameBench 2
Menu

Model results · Mistral

Mistral Large 4

No Overall rank: results for 2 of 3 reasoning settings. Balanced not supported.

Score · relative 0–100
46.7
Rank
—
Status
Provisional
Players generated
2026-10-09
Match evidence updated
2026-10-24
Results published
Compare in charts View player programs Back to leaderboard

Scores by reasoning setting

  • High (Intensive group, tested and included)57.9
  • None (Baseline group, tested and included)35.6

Every tested setting is included in the overall score.

Available settings and grouping

Available settings

NoneHigh

Checked on 2026-10-09 · Provider documentation

How settings are grouped

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

Scores by game

  • Go47.2
  • Chess54.3
  • Shogi37.0
  • Xiangqi52.1
  • Hex56.7
  • International Draughts1 of 2 failed39.8
  • Game of the Amazons44.5
  • Tumbleweed42.4

Each game counts every generation attempt, a failed one as 0 (“1 of 2 failed” marks games with failed attempts). Scores are relative within each game, across the included settings; they do not compare game difficulty.

What this result shows

Strongest included setting: High (57.9).

Across included settings, the highest game score is Hex (56.7); the lowest is Shogi (37.0). Each game counts every generation attempt, a failed one as 0. These are relative scores within each game, not direct comparisons of difficulty.

Match evidence measures these retained programs. It does not establish how a fresh generation will perform. Independent-generation variation is not estimated in this release.

Test protocol and evidence limits
Model identifier
mistralai/mistral-large-4-0
Provider route (catalog)
openrouter
Prompt identity / profile
Not retained in this result set / Not retained in this result set
Prompt version
Not retained in this result set
Generation policy
Generation-quality admission policy (see methodology)
Requested output-token limits
262144 (23 of 23 indexed attempts)

Generation evidence

  • None: 7 contributing player programs across 7 games
  • High: 8 contributing player programs across 8 games

Counts describe contributing programs, not independent replications: repairs and resends are not new independent samples. Independent-generation lineage is not retained.

GameReasoning groupProgramsWorking-program strengthRaw ratingCombined record (W / D / L)
GoIntensive1 working of 1 attempt35.01323.7160 / 22 / 334
GoBaseline1 working of 1 attempt59.31559.2242 / 106 / 168
ChessIntensive1 working of 1 attempt65.41598.0174 / 264 / 42
ChessBaseline1 working of 1 attempt43.11418.65 / 388 / 87
ShogiIntensive1 working of 1 attempt43.61371.9108 / 177 / 209
ShogiBaseline1 working of 1 attempt30.51254.252 / 165 / 277
XiangqiIntensive1 working of 1 attempt65.61602.2201 / 234 / 63
XiangqiBaseline1 working of 1 attempt38.61386.637 / 295 / 166
HexIntensive1 working of 1 attempt49.51431.6254 / 0 / 276
HexBaseline1 working of 1 attempt63.81617.6329 / 0 / 201
International DraughtsIntensive1 working of 1 attempt79.61936.9371 / 36 / 95
Game of the AmazonsIntensive1 working of 1 attempt79.41881.5418 / 0 / 112
Game of the AmazonsBaseline1 working of 1 attempt9.5820.543 / 0 / 487
TumbleweedIntensive1 working of 1 attempt44.61328.795 / 256 / 187
TumbleweedBaseline1 working of 1 attempt40.21280.471 / 259 / 208

Each row covers all the model's programs in one game and setting. Strength and raw rating are attempt-weighted means; under them, each program's score and the lowest and highest rating describe the programs (not a confidence interval). The combined record adds up their matches: evidence volume, not strength.

Failures and budgets

1 model-code generation failures; 0 provider/infrastructure failures excluded from the generation denominator. Runtime player faults are separate: 0 recorded one-sided faults across contributing program rows. A crash or illegal move pinned on one program also counts as that program's loss in its match record; other faults, such as timeouts, are left out of rating evidence.

Repair/resend outcomes and available costs are included. Exact retry ceilings and execution budgets are not retained in this result set; see the methodology for the public policy. Do not infer a measured setting from a current provider catalog.

Player program results

High: 88% / 12% / 0% · n 8None: 50% / 38% / 12% · n 8 No Overall rankBalanced not supported

Generation cost

$0.11average estimated cost per game and reasoning setting

Median
$0.05
Range
$0.01–$0.34
Known cost subtotal (incomplete or unverified charges)
$1.70
Cost data
16 combinations · 16 runs
Price source
Provider-reported
Price list
boardgame-list-prices-2026-10-09
Average output
47k tokens
Output range
3.1k–160k tokens
Runs with output-token data
16
How cost is measured

Comparison cost gives equal weight to each model, game, and reasoning-setting combination. Recorded generation attempts include repairs and resends when cost evidence is available; runtime compute and service operation are excluded. Cost and output-token counts use separate telemetry denominators. A list-price estimate is not actual expenditure; mixed evidence is not a uniform standard-price comparison.

Test protocol

  • Combines this model's tested reasoning settings
  • Player-program generation; retained protocol details are under “Test protocol and evidence limits” above