Model results
Qwen3.8 Max 0902
Alibaba · Overall Models
- Score · relative 0–100
- 40.5
- Rank
- 25
- Status
- Partial 3/3
- Rank change
- Baseline
- Players generated
- 2026-09-18 – 2026-09-18
- Match evidence updated
- 2026-09-26
- Results published
- 2026-09-26T08:55:16Z
- Settings tested
- All three benchmark settings tested
Why this result is partial: the official generation cohort is incomplete. The rank uses the available reasoning-setting results.
What this result shows
Strongest included setting: Xhigh (54.8).
Across included settings, the highest game score is International Draughts (65.8); the lowest is Chess (19.6). 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
- qwen/qwen3.8-max-0902
- 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
- 131072 (29 of 29 indexed attempts)
Generation evidence
- Low: 8 contributing player programs across 8 games
- Medium: 8 contributing player programs across 8 games
- Xhigh: 7 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; 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 | 9.5–9.5 |
| Chess | medium | 1 | 1 | 16.7–16.7 |
| Chess | xhigh | 1 | 1 | 32.8–32.8 |
| Game of the Amazons | low | 1 | 1 | 38.0–38.0 |
| Game of the Amazons | medium | 1 | 1 | 43.4–43.4 |
| Go | low | 1 | 1 | 32.1–32.1 |
| Go | medium | 1 | 1 | 26.1–26.1 |
| Go | xhigh | 1 | 1 | 50.7–50.7 |
| Hex | low | 1 | 1 | 56.1–56.1 |
| Hex | medium | 1 | 1 | 41.8–41.8 |
| Hex | xhigh | 1 | 1 | 78.0–78.0 |
| International Draughts | low | 1 | 1 | 71.2–71.2 |
| International Draughts | medium | 1 | 1 | 54.3–54.3 |
| International Draughts | xhigh | 1 | 1 | 71.9–71.9 |
| Shogi | low | 1 | 1 | 34.1–34.1 |
| Shogi | medium | 1 | 1 | 42.5–42.5 |
| Shogi | xhigh | 1 | 1 | 51.7–51.7 |
| Tumbleweed | low | 1 | 1 | 23.3–23.3 |
| Tumbleweed | medium | 1 | 1 | 26.3–26.3 |
| Tumbleweed | xhigh | 1 | 1 | 37.2–37.2 |
| Xiangqi | low | 1 | 1 | 0.4–0.4 |
| Xiangqi | medium | 1 | 1 | 17.5–17.5 |
| Xiangqi | xhigh | 1 | 1 | 61.4–61.4 |
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 | 33.1 | Tested and included | Baseline |
| Medium | 33.6 | Tested and included | Balanced |
| Xhigh | 54.8 | Tested and included | Intensive |
Available settings and grouping
Available settings
Checked on 2026-09-18 · 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: 86% / 14% / 0% · n 7Medium: 75% / 25% / 0% · n 8Low: 75% / 25% / 0% · n 8 All three benchmark settings testedGeneration cost
- Average estimated cost
- $0.19
- Median estimated cost
- $0.12
- Estimated range
- $0.00–$0.61
- Cost data
- 24 combinations / 24 recorded runs
- Provider-reported total
- $4.48
- Price source
- Provider-reported
- Price list
- boardgame-list-prices-2026-09-08
- Average output
- 29k tokens
- Output range
- 6.3k–94k tokens
- Runs with output-token evidence
- 24
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