Scores by reasoning setting

Enablednot included (Balanced group, tested, not included)23.4
Nonenot included (Baseline group, tested, not included)6.7

Settings marked “not included” were tested but are left out of the overall score.

Scores by game

Go2 of 2 failed0.0
Chess2 of 2 failed0.0
Shogi1 of 2 failed10.9
Xiangqi1 of 2 failed20.6
Hex33.2
International Draughts1 of 2 failed8.6
Game of the Amazons16.1
Tumbleweed30.9

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

No qualified setting comparison is retained.

Across included settings, the highest game score is Hex (33.2); the lowest is 0.0, shared by 2 games. 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: cohere/north-mini-code
Provider route (catalog): Not retained in this result set
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: 64000 (15 of 30 indexed attempts)

Generation evidence

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

Game	Reasoning group	Programs	Working-program strength	Raw rating	Combined record (W / D / L)
Shogi	Balanced	1 working of 1 attempt	21.7	1164.4	37 / 115 / 342
Xiangqi	Balanced	1 working of 1 attempt	41.2	1406.7	45 / 304 / 149
Hex	Balanced	1 working of 1 attempt	46.5	1393.4	238 / 0 / 292
Hex	Baseline	1 working of 1 attempt	19.9	1007.8	100 / 0 / 430
International Draughts	Balanced	1 working of 1 attempt	17.2	914.1	72 / 2 / 428
Game of the Amazons	Balanced	1 working of 1 attempt	30.2	1196.0	147 / 0 / 383
Game of the Amazons	Baseline	1 working of 1 attempt	2.0	463.0	7 / 0 / 523
Tumbleweed	Balanced	1 working of 1 attempt	30.1	1172.1	94 / 111 / 333
Tumbleweed	Baseline	1 working of 1 attempt	31.7	1189.4	16 / 283 / 239

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

7 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

Enabled: 38% / 37% / 25% · n 8None: 25% / 13% / 62% · n 8 No Overall rankMissing IntensiveMany programs failed

Generation cost

$0.00average estimated cost per game and reasoning setting

Median: $0.00
Range: $0.00–$0.00
Known cost subtotal (incomplete or unverified charges): $0.00
Cost data: 16 combinations · 16 runs
Price source: Provider-reported
Price list: boardgame-list-prices-2026-10-09
Average output: 17k tokens
Output range: 1.1k–52k 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

North Mini Code