Model results
DeepSeek V4 Pro
Provider: DeepSeek
- Rank
- 17
- Status
- Partial 2/3
- Rank change
- Baseline
- Score
- 43.5
- Last tested
- 2026-08-05
- Settings tested
- Missing Balanced
Why this result is partial: one or more bracket scores are missing; one or more documented settings are untested or ineligible; generation-quality evidence is missing. The rank uses the available reasoning-setting results.
Scores by reasoning setting
Available settings
Reasoning disabledHighXHigh
Checked on 2026-07-21 · Provider documentation
Scores from tested settings
| Tested setting | Score | Result status | Display group |
|---|---|---|---|
| Reasoning disabled | 40.8 | Tested and included | Baseline |
| XHigh | 46.3 | Tested and included | Intensive |
How settings are grouped
- Baseline: Reasoning disabled — tested and included
- Balanced: High — available, not tested in the current results
- Intensive: XHigh — tested and included
Player program results
XHigh: 13% / 62% / 25% · n 8Reasoning disabled: 50% / 38% / 12% · n 8 Missing BalancedMany programs needed repairMany programs failedGeneration cost
- Average estimated cost
- $0.05
- Median estimated cost
- $0.03
- Estimated range
- $0.0056–$0.11
- Cost data
- 16 combinations / 16 recorded runs
- Observed total
- $0.79
- Price source
- Provider-reported
- Price list
- Not recorded for this older data
- Average output
- 29k tokens
- Output range
- 2.7k–81k tokens
- Samples
- 16
Estimated cost gives equal weight to each model, game, and reasoning-setting combination.
Test setup
- Combines this model's tested reasoning settings
- Uses the standard GameBench player-program prompt