- Score · relative 0–100
- 78.1
- Rank
- 7
- Status
- Complete 3/3
- Rank change
- 0
- Players generated
- 2026-07-25
- Match evidence updated
- 2026-10-26
- Results published
Scores by reasoning setting
Available settings and grouping
Available settings
Checked on 2026-07-25 · Provider documentation
How settings are grouped
- Baseline: Thinking disabled — tested and included
- Balanced: Medium — tested and included
- Intensive: XHigh — tested and included
Scores by game
What this result shows
Strongest included setting: XHigh (86.1).
Across included settings, the highest game score is Hex (90.5); the lowest is Xiangqi (58.1). 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
- claude-opus-5
- Provider route (catalog)
- anthropic
- 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
- 128000 (48 of 48 indexed attempts)
Generation evidence
- Thinking disabled: 14 contributing player programs across 8 games
- Medium: 14 contributing player programs across 7 games
- XHigh: 13 contributing player programs across 7 games
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) |
|---|---|---|---|---|---|
| Go | Intensive | 2 working of 2 attempts | 70.0 program scores 92.0 · 48.1 | 1744.4 program range 1451–2038 | 698 / 17 / 317 |
| Go | Balanced | 2 working of 2 attempts | 71.7 program scores 81.9 · 61.5 | 1703.7 program range 1581–1827 | 670 / 98 / 264 |
| Go | Baseline | 2 working of 2 attempts | 76.7 program scores 90.4 · 63.0 | 1795.3 program range 1596–1994 | 597 / 354 / 81 |
| Chess | Intensive | 2 working of 2 attempts | 83.4 program scores 87.6 · 79.2 | 1810.5 program range 1744–1877 | 699 / 186 / 75 |
| Chess | Balanced | 2 working of 2 attempts | 69.6 program scores 69.7 · 69.5 | 1637.2 program range 1636–1638 | 442 / 422 / 95 |
| Chess | Baseline | 2 working of 2 attempts | 71.5 program scores 76.0 · 67.0 | 1658.8 program range 1613–1705 | 476 / 393 / 91 |
| Shogi | Intensive | 2 working of 2 attempts | 94.8 program scores 95.2 · 94.3 | 2195.5 program range 2170–2221 | 928 / 9 / 51 |
| Shogi | Balanced | 2 working of 2 attempts | 86.7 program scores 87.0 · 86.4 | 1903.2 program range 1897–1910 | 831 / 16 / 141 |
| Shogi | Baseline | 2 working of 2 attempts | 51.7 program scores 53.9 · 49.5 | 1442.7 program range 1423–1462 | 406 / 131 / 451 |
| Xiangqi | Intensive | 2 working of 2 attempts | 80.4 program scores 87.0 · 73.9 | 1771.5 program range 1683–1860 | 707 / 165 / 124 |
| Xiangqi | Balanced | 2 working of 2 attempts | 44.7 program scores 49.2 · 40.3 | 1434.3 program range 1400–1469 | 201 / 456 / 339 |
| Xiangqi | Baseline | 2 working of 2 attempts | 49.1 program scores 58.0 · 40.3 | 1468.8 program range 1400–1538 | 275 / 395 / 326 |
| Hex | Intensive | 2 working of 2 attempts | 93.3 program scores 99.1 · 87.6 | 2565.2 program range 2150–2981 | 988 / 0 / 72 |
| Hex | Balanced | 2 working of 2 attempts | 89.0 program scores 92.6 · 85.3 | 2219.9 program range 2071–2369 | 937 / 0 / 123 |
| Hex | Baseline | 2 working of 2 attempts | 89.1 program scores 89.4 · 88.9 | 2212.7 program range 2202–2223 | 939 / 0 / 121 |
| International Draughts | Baseline | 1 working of 1 attempt | 88.6 | 2136.9 | 427 / 23 / 52 |
| Game of the Amazons | Intensive | 1 working of 1 attempt | 95.9 | 2495.8 | 512 / 0 / 18 |
| Game of the Amazons | Balanced | 2 working of 2 attempts | 84.3 program scores 92.1 · 76.5 | 2048.9 program range 1825–2273 | 892 / 0 / 168 |
| Game of the Amazons | Baseline | 1 working of 1 attempt | 76.0 | 1816.0 | 398 / 0 / 132 |
| Tumbleweed | Intensive | 2 working of 2 attempts | 85.1 program scores 92.0 · 78.2 | 2040.2 program range 1852–2229 | 898 / 0 / 178 |
| Tumbleweed | Balanced | 2 working of 2 attempts | 89.4 program scores 94.3 · 84.5 | 2162.9 program range 2001–2325 | 949 / 2 / 125 |
| Tumbleweed | Baseline | 2 working of 2 attempts | 71.5 program scores 75.0 · 68.0 | 1717.7 program range 1651–1785 | 725 / 23 / 328 |
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
0 model-code generation failures; 0 provider/infrastructure failures excluded from the generation denominator. Runtime player faults are separate: 1 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
XHigh: 100% / 0% / 0% · n 13Medium: 100% / 0% / 0% · n 14Thinking disabled: 100% / 0% / 0% · n 14 All three benchmark settings testedGeneration cost
$0.70average estimated cost per game and reasoning setting
- Median
- $0.48
- Range
- $0.22–$2.10
- Known cost subtotal (incomplete or unverified charges)
- $33.78
- Cost data
- 24 combinations · 48 runs
- Price source
- Standard list-price estimate
- Price list
- boardgame-list-prices-2026-07-25
- Average output
- 26k tokens
- Output range
- 5.4k–88k tokens
- Runs with output-token data
- 48
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