# Claude Opus 4.1 vs Gemini 3.1 Pro Preview

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 41.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-opus-4-1-vs-gemini-3-1-pro-preview
- Last updated: 2026-10-10
- Shared benchmarks: 43

## Summary

- They share 43 benchmarks with published results for both. Claude Opus 4.1 scores higher in 1 category and Gemini 3.1 Pro Preview in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3.1 Pro Preview leads 62.1 to 22.3.
- The biggest single-benchmark swing is Chess Puzzles: 7% for Claude Opus 4.1 and 55% for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview is cheaper at $2 / $12 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 200K.

## Snapshot

| | Claude Opus 4.1 | Gemini 3.1 Pro Preview |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 41.0 | 56.7 |
| Rank | 142 | 23 |
| Context | 200K | 1.05M |
| Input $/M | $15 | $2 |
| Output $/M | $75 | $12 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.1: 44.4 (#73)
- Gemini 3.1 Pro Preview: 42.5 (#99)

| Benchmark | Claude Opus 4.1 | Gemini 3.1 Pro Preview |
|---|---|---|
| SWE-bench Verified | 73.3% | 75.6% |
| LMArena WebDev | 1390 | 1447 |
| WeirdML | 45.9% | 72.1% |
| LMArena Coding | 1479 | 1484 |
| ALE-Bench | 674.77 | 1,161 |
| AlgoTune | 1.34 | 2.02 |
| DeepSWE | — | 11.7% |
| SciCode | — | 58.9% |
| GSO | — | 22.6% |
| MirrorCode | — | 8.9% |

## Agentic & Tool Use

- Claude Opus 4.1: 35.0 (#41)
- Gemini 3.1 Pro Preview: 37.7 (#34)

| Benchmark | Claude Opus 4.1 | Gemini 3.1 Pro Preview |
|---|---|---|
| Terminal-Bench | 38% | 80.2% |
| DeepResearch Bench | 48.3% | 47.8% |
| LMArena Search | 1148 | 1211 |
| METR Time Horizons | 66.8% | 77% |
| APEX-Agents | — | 35.3% |
| GDPval | 43.6% | — |
| τ²-bench Banking | — | 26% |
| Cybench | 42% | — |
| PostTrainBench | — | 22% |
| BALROG | — | 57% |
| ExploitBench | — | 26.1% |
| GBAEval | — | 0.8% |
| GDP.pdf | — | 17% |
| Vending-Bench 2 | — | 3,774 |

## Reasoning

- Claude Opus 4.1: 32.2 (#76)
- Gemini 3.1 Pro Preview: 71.7 (#12)

| Benchmark | Claude Opus 4.1 | Gemini 3.1 Pro Preview |
|---|---|---|
| SimpleBench | 60% | 79.6% |
| Chess Puzzles | 7% | 55% |
| EnigmaEval | 7.2% | 36.8% |
| EBR-Bench | 7.9% | 14.3% |
| LMArena Hard Prompts | 1443 | 1485 |
| Mystery Game Puzzles | 21% | 34% |
| DTBench | 80% | 97.1% |
| LMCA | 37.1% | 53.8% |
| Epoch Capabilities Index | 144.12 | 154.77 |
| ForecastBench | 62 | 59 |
| ARC-AGI-2 | — | 77.1% |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98% |
| CritPt | — | 17.7% |
| Thematic Generalization | — | 79.4% |

## Math

- Claude Opus 4.1: 22.3 (#277)
- Gemini 3.1 Pro Preview: 62.1 (#34)

| Benchmark | Claude Opus 4.1 | Gemini 3.1 Pro Preview |
|---|---|---|
| FrontierMath (Tiers 1-3) | 12.6% | 59.6% |
| FrontierMath Tier 4 | 2.4% | 26.8% |
| OTIS Mock AIME 2024-2025 | 68.9% | 95.6% |
| LMArena Math | 1431 | 1485 |
| FrontierMath (Feb 2025 set) | 7.2% | 36.9% |
| FrontierMath Tier 4 (v1) | 4.2% | 16.7% |
| MathArena Final-Answer Competitions | — | 86.5% |
| ProofBench | — | 26% |

## Knowledge

- Claude Opus 4.1: 42.0 (#101)
- Gemini 3.1 Pro Preview: 71.8 (#3)

| Benchmark | Claude Opus 4.1 | Gemini 3.1 Pro Preview |
|---|---|---|
| GPQA Diamond | 77.3% | 94.4% |
| Humanity's Last Exam | 11.5% | 46.4% |
| Vectara Hallucination Rate | 11.8% | 10.4% |
| LMArena Expert | 1439 | 1485 |
| SimpleQA Verified | — | 73.5% |
| Confabulations | 17.1% | — |

## Multimodal

- Claude Opus 4.1: 26.8 (#119)
- Gemini 3.1 Pro Preview: 37.9 (#69)

| Benchmark | Claude Opus 4.1 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Vision | — | 1296 |
| VPCT | 35% | — |
| Blueprint-Bench 2 | — | 26.5% |
| Furniture Assembly | — | 26.7% |
| LMArena Document | — | 1444 |

## Multilingual

- Claude Opus 4.1: 52.0 (#95)
- Gemini 3.1 Pro Preview: 57.0 (#12)

| Benchmark | Claude Opus 4.1 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Non-English | 1405 | 1477 |
| LMArena Chinese | 1427 | 1529 |
| LMArena French | 1431 | 1487 |
| LMArena German | 1413 | 1491 |
| LMArena Japanese | 1378 | 1493 |
| LMArena Korean | 1380 | 1455 |
| LMArena Russian | 1422 | 1498 |
| LMArena Spanish | 1448 | 1479 |

## Instruction Following

- Claude Opus 4.1: 75.6 (#58)
- Gemini 3.1 Pro Preview: 77.0 (#32)

| Benchmark | Claude Opus 4.1 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1435 | 1466 |

## Long Context

- Claude Opus 4.1: 44.5 (#63)
- Gemini 3.1 Pro Preview: 47.4 (#18)

| Benchmark | Claude Opus 4.1 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Longer Query | 1455 | 1483 |
| CL-bench | — | 20.8% |
| CL-bench Life | — | 16.9% |

## Writing & Preference

- Claude Opus 4.1: 62.4 (#74)
- Gemini 3.1 Pro Preview: 66.1 (#37)

| Benchmark | Claude Opus 4.1 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Text | 1419 | 1481 |
| LMArena Creative Writing | 1412 | 1482 |
| LMArena Multi-Turn | 1444 | 1488 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 1491 |
| EQ-Bench 4 | — | 1142 |

## FAQ

### Is Claude Opus 4.1 better than Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 41.0 on the Noometry Index.

### Which is cheaper, Claude Opus 4.1 or Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview is cheaper. It lists at $2 per million input tokens and $12 per million output tokens; Claude Opus 4.1 lists at $15 and $75.

### Is Claude Opus 4.1 or Gemini 3.1 Pro Preview better for coding?

Claude Opus 4.1 scores higher on coding benchmarks: 44.4 versus 42.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 200K.

### How many benchmarks do Claude Opus 4.1 and Gemini 3.1 Pro Preview share?

43 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Gemini 3.1 Pro Preview has 71.