gemini-3.1-pro-preview-high: benchmark scores, price and ranking
gemini-3.1-pro-preview-high from Google ranks #18 of 741 LLMs on the LLMs Tiger aggregate benchmark score (55.3), based on 8 benchmark results captured up to 2026-10-05.
- Organisation
- Type
- Preview release
- Open weights
- No
- Cheapest API price
- $2.00 in / $12.00 out per million tokens (via aihubmix, observed 2026-10-05T21:47Z)
- Aggregate rank
- #18 of 741 (score 55.3)
Relative to other models, gemini-3.1-pro-preview-high is strongest on LiveBench IF (#1 of 17) and weakest on LiveBench Agentic Coding (#11 of 17).
gemini-3.1-pro-preview-high benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| LiveBench IF | 79.1% | #1 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| LiveBench Language | 85.4% | #2 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| LiveBench Data Analysis | 78.5% | #3 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| MCP Atlas | 78.2% | #3 of 14 | Scale Labs MCP Atlas leaderboard | 2026-10-05 |
| LiveBench Reasoning | 84.0% | #4 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| LiveBench Mathematics | 91.0% | #5 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| LiveBench Coding | 76.5% | #9 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| LiveBench Agentic Coding | 45.4% | #11 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
gemini-3.1-pro-preview-high is also listed at 1 other reasoning-effort setting; this page shows the highest-effort row, which is the one the leaderboard keeps by default.
Models ranked nearby
- #15 GPT-5.4 Pro (xhigh) (56.1)
- #16 GPT-5.6 Sol (pro, max) (56.1)
- #17 Kimi K3 (max) (55.7)
- #19 GPT-5.6 Luna (max) (55.1)
- #20 Muse Spark 1.3 (max) (55.0)
- #21 Claude 4 Sonnet (54.5)
Compare it on the live leaderboard → · How the aggregate score works