LiveBench Integrals With Game: leaderboard
One of four mathematics subtasks in LiveBench, added in January 2026 as a game theory problem combined with integral calculations. The model answers in a single turn with an integer or fraction inside solution tags or a boxed expression, and the grader checks it against the ground truth for mathematical equivalence, with no LLM judge. The subtask score runs from 0 to 100, higher is better.
Metric: Score. Source: livebench.ai. Saturation forecast: Estimated already saturated. 71 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol (Max) | 100 | #19 (GPT-5.6 Sol) |
| 2 | GPT-6 Astra (Max) | 100 | #6 (GPT-6 Astra) |
| 3 | GPT-6.1 Sol (Max) | 100 | #7 (GPT-6.1 Sol) |
| 4 | Claude Opus 5.5 (Max) | 100 | #3 (Claude Opus 5.5) |
| 5 | Claude Sonnet 5.5 (xHigh) | 100 | #11 (Claude Sonnet 5.5) |
| 6 | GPT-5.5 (xHigh) | 99 | #31 (GPT-5.5) |
| 7 | GPT-6 Sol (Max) | 99 | #14 (GPT-6 Sol) |
| 8 | Claude Fable 5.1 (Max) | 99 | #9 (Claude Fable 5.1) |
| 9 | GPT-6.1 Sol (xHigh) | 99 | #7 (GPT-6.1 Sol) |
| 10 | Claude Opus 5.5 (xHigh) | 99 | #3 (Claude Opus 5.5) |
| 11 | Muse Wonder (Max) | 98 | #15 (Muse Wonder) |
| 12 | Claude Opus 5 (Max) | 97 | #12 (Claude Opus 5) |
| 13 | Claude Fable 5 (Max) | 97 | #16 (Claude Fable 5) |
| 14 | Claude Sonnet 5.5 (Max) | 97 | #11 (Claude Sonnet 5.5) |
| 15 | Grok 4.7 (xHigh) | 96 | #25 (Grok 4.7) |
No result here: #8 Gemini 4 Argon, #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=livebench-integrals-with-game · How It Works · Data refreshed daily, snapshot 2026-10-20.