- Score · relative 0–100
- 88.6
- Rank
- 3
- Status
- Complete 3/3
- Rank change
- 0
- Players generated
- 2026-09-03 – 2026-09-08
- Match evidence updated
- 2026-10-26
- Results published
Scores by reasoning setting
Available settings and grouping
Available settings
Checked on 2026-09-08 · Provider documentation
How settings are grouped
- Baseline: Low — tested and included
- Balanced: Medium — tested and included
- Intensive: XHigh — tested and included
Scores by game
What this result shows
Strongest included setting: XHigh (94.4).
Across included settings, the highest game score is Shogi (93.7); the lowest is Xiangqi (75.6). 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-fable-5-1
- 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 (10 of 35 indexed attempts)
Generation evidence
- Low: 8 contributing player programs across 8 games
- Medium: 8 contributing player programs across 8 games
- XHigh: 11 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.
| Game | Reasoning group | Programs | Working-program strength | Raw rating | Combined record (W / D / L) |
|---|---|---|---|---|---|
| Go | Intensive | 1 working of 1 attempt | 93.2 | 2076.1 | 475 / 2 / 39 |
| Go | Balanced | 1 working of 1 attempt | 73.9 | 1716.9 | 370 / 1 / 145 |
| Go | Baseline | 1 working of 1 attempt | 88.3 | 1943.8 | 445 / 4 / 66 |
| Chess | Intensive | 1 working of 1 attempt | 95.1 | 2095.6 | 445 / 23 / 12 |
| Chess | Balanced | 1 working of 1 attempt | 91.4 | 1965.4 | 419 / 36 / 25 |
| Chess | Baseline | 1 working of 1 attempt | 83.4 | 1803.6 | 340 / 112 / 28 |
| Shogi | Intensive | 2 working of 2 attempts | 95.4 program scores 95.5 · 95.3 | 2231.5 program range 2226–2237 | 937 / 6 / 45 |
| Shogi | Balanced | 1 working of 1 attempt | 92.3 | 2080.3 | 447 / 10 / 37 |
| Shogi | Baseline | 1 working of 1 attempt | 93.3 | 2120.5 | 456 / 3 / 35 |
| Xiangqi | Intensive | 2 working of 2 attempts | 88.0 program scores 90.5 · 85.5 | 1883.4 program range 1834–1933 | 824 / 90 / 82 |
| Xiangqi | Balanced | 1 working of 1 attempt | 64.6 | 1593.9 | 194 / 237 / 66 |
| Xiangqi | Baseline | 1 working of 1 attempt | 74.2 | 1686.1 | 271 / 182 / 45 |
| Hex | Intensive | 1 working of 1 attempt | 93.4 | 2413.3 | 495 / 0 / 35 |
| Hex | Balanced | 1 working of 1 attempt | 88.6 | 2188.9 | 466 / 0 / 64 |
| Hex | Baseline | 1 working of 1 attempt | 91.7 | 2327.3 | 485 / 0 / 45 |
| International Draughts | Intensive | 1 working of 1 attempt | 98.2 | 2599.8 | 492 / 4 / 6 |
| International Draughts | Balanced | 1 working of 1 attempt | 88.4 | 2132.3 | 430 / 15 / 57 |
| International Draughts | Baseline | 1 working of 1 attempt | 83.9 | 2025.9 | 401 / 23 / 78 |
| Game of the Amazons | Intensive | 2 working of 2 attempts | 93.9 program scores 94.0 · 93.7 | 2367.5 program range 2357–2378 | 1002 / 0 / 58 |
| Game of the Amazons | Balanced | 1 working of 1 attempt | 93.9 | 2367.4 | 501 / 0 / 29 |
| Game of the Amazons | Baseline | 1 working of 1 attempt | 88.2 | 2111.9 | 469 / 0 / 61 |
| Tumbleweed | Intensive | 1 working of 1 attempt | 97.8 | 2567.0 | 527 / 0 / 11 |
| Tumbleweed | Balanced | 1 working of 1 attempt | 85.6 | 2031.0 | 452 / 0 / 86 |
| Tumbleweed | Baseline | 1 working of 1 attempt | 89.8 | 2152.5 | 477 / 1 / 60 |
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; 5 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
XHigh: 82% / 18% / 0% · n 11Medium: 88% / 12% / 0% · n 8Low: 100% / 0% / 0% · n 8 All three benchmark settings testedGeneration cost
$2.32average estimated cost per game and reasoning setting
- Median
- $1.13
- Range
- $0.66–$11.79
- Known cost subtotal (incomplete or unverified charges)
- $64.31
- Cost data
- 24 combinations · 27 runs
- Price source
- Standard list-price estimate
- Price list
- boardgame-list-prices-2026-08-08 + boardgame-list-prices-2026-09-08
- Average output
- 47k tokens
- Output range
- 5.6k–231k tokens
- Runs with output-token data
- 32
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