Model results
Claude Opus 5.5
Anthropic · Overall Models
- Score · relative 0–100
- 72.3
- Rank
- 3
- Status
- Complete 3/3
- Rank change
- Baseline
- Players generated
- 2026-09-22 – 2026-09-22
- Match evidence updated
- 2026-09-26
- Results published
- 2026-09-26T08:55:16Z
- Settings tested
- All three benchmark settings tested
What this result shows
Strongest included setting: XHigh (81.9).
Across included settings, the highest game score is Game of the Amazons (83.5); the lowest is Shogi (61.5). 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-5-5
- 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
- 65536, 128000 (30 of 30 indexed attempts)
Generation evidence
- Low: 9 contributing player programs across 8 games
- Medium: 9 contributing player programs across 8 games
- XHigh: 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; the per-game counts below keep unique code identities separate from admitted generation runs.
| Game | Setting | Unique programs | Admitted generation runs | Program score range |
|---|---|---|---|---|
| Chess | low | 1 | 1 | 51.4–51.4 |
| Chess | medium | 1 | 1 | 78.4–78.4 |
| Chess | xhigh | 1 | 1 | 83.9–83.9 |
| Game of the Amazons | low | 1 | 1 | 79.8–79.8 |
| Game of the Amazons | medium | 1 | 1 | 82.7–82.7 |
| Game of the Amazons | xhigh | 1 | 1 | 88.1–88.1 |
| Go | low | 1 | 1 | 72.0–72.0 |
| Go | medium | 1 | 1 | 74.6–74.6 |
| Go | xhigh | 1 | 1 | 59.2–59.2 |
| Hex | low | 1 | 1 | 78.8–78.8 |
| Hex | medium | 1 | 1 | 71.9–71.9 |
| Hex | xhigh | 1 | 1 | 86.5–86.5 |
| International Draughts | low | 1 | 1 | 68.6–68.6 |
| International Draughts | medium | 1 | 1 | 79.0–79.0 |
| International Draughts | xhigh | 1 | 1 | 86.9–86.9 |
| Shogi | low | 1 | 1 | 33.3–33.3 |
| Shogi | medium | 1 | 1 | 71.7–71.7 |
| Shogi | xhigh | 1 | 1 | 79.7–79.7 |
| Tumbleweed | low | 2 | 2 | 43.2–43.4 |
| Tumbleweed | medium | 2 | 2 | 73.2–81.9 |
| Tumbleweed | xhigh | 1 | 1 | 78.6–78.6 |
| Xiangqi | low | 1 | 1 | 48.1–48.1 |
| Xiangqi | medium | 1 | 1 | 68.5–68.5 |
| Xiangqi | xhigh | 1 | 1 | 92.6–92.6 |
Program ranges describe the retained competitors on this release scale, not a statistical estimate of a fresh generation.
Failures and budgets
0 model-code generation failures; 1 provider/infrastructure failures excluded from the generation denominator. Runtime player faults are separate: 0 recorded unilateral faults across contributing program rows, excluded from 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.
Scores by reasoning setting
| Tested setting | Score | Result status | Display group |
|---|---|---|---|
| Low | 59.4 | Tested and included | Baseline |
| Medium | 75.5 | Tested and included | Balanced |
| XHigh | 81.9 | Tested and included | Intensive |
Available settings and grouping
Available settings
Checked on 2026-09-22 · Provider documentation
How settings are grouped
- Baseline: Low — tested and included
- Balanced: Medium — tested and included
- Intensive: XHigh — tested and included
Player program results
XHigh: 75% / 25% / 0% · n 8Medium: 89% / 11% / 0% · n 9Low: 100% / 0% / 0% · n 9 All three benchmark settings testedGeneration cost
- Average estimated cost
- $0.81
- Median estimated cost
- $0.27
- Estimated range
- $0.09–$3.09
- Cost data
- 24 combinations / 27 recorded runs
- Estimated total for recorded runs
- $21.74
- Price source
- Standard list-price estimate
- Price list
- boardgame-list-prices-2026-09-08
- Average output
- 37k tokens
- Output range
- 2.4k–150k tokens
- Runs with output-token evidence
- 27
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 evidence below