- Score · relative 0–100
- 27.3
- Rank
- 60
- Status
- Partial 3/3
- Players generated
- 2026-07-02 – 2026-07-11
- Match evidence updated
- 2026-10-26
- Results published
Why this result is partial: one or more documented settings are untested or ineligible; some games cannot be scored: their only generation attempts failed because of the test harness or the provider and cannot currently be repeated. The rank uses the available reasoning-setting results.
Scores by reasoning setting
Available settings and grouping
Available settings
Checked on 2026-07-30 · Provider documentation
How settings are grouped
- Baseline: Reasoning disabled — available, not tested in the current results
- Balanced: Medium — tested and included
- Intensive: High — tested and included
Scores by game
What this result shows
Strongest included setting: Medium (27.7).
Across included settings, the highest game score is Hex (46.1); the lowest is Game of the Amazons (4.1). 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
- nvidia/nemotron-3-ultra-550b-a55b
- 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
- Not retained (0 of 56 indexed attempts)
Generation evidence
- Medium: 5 contributing player programs across 5 games
- High: 9 contributing player programs across 6 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 2 attempts | 25.6 | 1222.4 | 71 / 106 / 339 |
| Go | Balanced | 1 working of 1 attempt | 57.2 | 1538.2 | 233 / 102 / 181 |
| Go | Baseline | 1 working of 1 attempt | 55.2 | 1519.2 | 235 / 78 / 203 |
| Chess | Intensive | 2 working of 2 attempts | 41.0 program scores 42.4 · 39.5 | 1401.7 program range 1391–1413 | 14 / 727 / 219 |
| Chess | Balanced | 1 working of 1 attempt | 41.0 | 1402.2 | 1 / 376 / 103 |
| Shogi | Baseline | 1 working of 1 attempt | 30.6 | 1255.2 | 45 / 180 / 269 |
| Xiangqi | Intensive | 1 working of 1 attempt | 41.2 | 1406.7 | 21 / 352 / 125 |
| Xiangqi | Baseline | 1 working of 1 attempt | 42.3 | 1415.5 | 32 / 341 / 125 |
| Hex | Intensive | 2 working of 2 attempts | 30.3 program scores 38.6 · 22.0 | 1169.1 program range 1045–1293 | 308 / 0 / 752 |
| Hex | Baseline | 1 working of 1 attempt | 61.9 | 1591.1 | 319 / 0 / 211 |
| International Draughts | Intensive | 1 working of 1 attempt | 34.0 | 1178.0 | 138 / 23 / 341 |
| International Draughts | Balanced | 1 working of 1 attempt | 56.4 | 1520.6 | 259 / 7 / 236 |
| International Draughts | Baseline | 1 working of 1 attempt | 16.5 | 900.0 | 67 / 5 / 430 |
| Game of the Amazons | Balanced | 1 working of 1 attempt | 9.9 | 831.9 | 45 / 0 / 485 |
| Game of the Amazons | Baseline | 1 working of 2 attempts | 5.0 | 657.8 | 21 / 0 / 509 |
| Tumbleweed | Intensive | 2 working of 2 attempts | 32.4 program scores 32.7 · 32.1 | 1196.8 program range 1194–1200 | 107 / 430 / 539 |
| Tumbleweed | Balanced | 1 working of 1 attempt | 29.5 | 1164.5 | 94 / 104 / 340 |
| Tumbleweed | Baseline | 1 working of 1 attempt | 33.6 | 1209.6 | 62 / 210 / 266 |
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
9 model-code generation failures; 4 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
High: 14% / 50% / 36% · n 14Medium: 0% / 71% / 29% · n 7Reasoning disabled: 56% / 22% / 22% · n 9 All three benchmark settings testedMany programs needed repairMany programs failedGeneration cost
$0.03average estimated cost per game and reasoning setting
- Median
- $0.03
- Range
- $0.01–$0.13
- Known cost subtotal (incomplete or unverified charges)
- $1.21
- Cost data
- 24 combinations · 34 runs
- Price source
- Provider-reported
- Price list
- Not recorded for this older data
- Average output
- 7.8k tokens
- Output range
- 2.7k–18k tokens
- Runs with output-token data
- 25
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