# Gemini 3.1 Pro Preview vs Qwen3.7 Plus

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 45.0 on the Noometry Index. Qwen3.7 Plus costs 6.4× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-1-pro-preview-vs-qwen3-7-plus
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 9 categories and Qwen3.7 Plus in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 38.4.
- The biggest single-benchmark swing is Chess Puzzles: 55% for Gemini 3.1 Pro Preview and 24% for Qwen3.7 Plus.
- Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Gemini 3.1 Pro Preview | Qwen3.7 Plus |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 56.7 | 45.0 |
| Rank | 20 | 66 |
| Context | 1.05M | 1M |
| Input $/M | $2 | $0.40 |
| Output $/M | $12 | $1.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.1 Pro Preview: 42.7 (#88)
- Qwen3.7 Plus: 36.1 (#200)

| Benchmark | Gemini 3.1 Pro Preview | Qwen3.7 Plus |
|---|---|---|
| SciCode | 58.9% | 45.5% |
| LMArena Coding | 1483 | 1473 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| FrontierCode | — | 10.2% |
| LMArena WebDev | 1446 | — |
| GSO | 22.6% | — |
| WeirdML | 72.1% | — |
| MirrorCode | 8.9% | — |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |

## Agentic & Tool Use

- Gemini 3.1 Pro Preview: 37.7 (#33)
- Qwen3.7 Plus: 21.2 (#130)

| Benchmark | Gemini 3.1 Pro Preview | Qwen3.7 Plus |
|---|---|---|
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| OSWorld 2.0 | — | 2.8% |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| METR Time Horizons | 77% | — |
| Vending-Bench 2 | 3,774 | — |

## Reasoning

- Gemini 3.1 Pro Preview: 71.7 (#9)
- Qwen3.7 Plus: 38.4 (#54)

| Benchmark | Gemini 3.1 Pro Preview | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 97.4% | 74.8% |
| CritPt | 17.7% | 9.1% |
| Chess Puzzles | 55% | 24% |
| LMArena Hard Prompts | 1484 | 1460 |
| Mystery Game Puzzles | 34% | 17% |
| DTBench | 97.1% | 84% |
| LMCA | 53.8% | 37.6% |
| Epoch Capabilities Index | 154.92 | 147.39 |
| ARC-AGI-2 | 77.1% | — |
| SimpleBench | 79.6% | — |
| ARC-AGI-1 | 98% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| ForecastBench | 59 | — |

## Math

- Gemini 3.1 Pro Preview: 61.8 (#28)
- Qwen3.7 Plus: 49.3 (#47)

| Benchmark | Gemini 3.1 Pro Preview | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.6% | 34.4% |
| OTIS Mock AIME 2024-2025 | 95.6% | 93.3% |
| LMArena Math | 1485 | 1467 |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| ProofBench | 26% | — |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |

## Knowledge

- Gemini 3.1 Pro Preview: 71.8 (#3)
- Qwen3.7 Plus: 54.9 (#46)

| Benchmark | Gemini 3.1 Pro Preview | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 94.4% | 87.9% |
| LMArena Expert | 1484 | 1467 |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| Vectara Hallucination Rate | 10.4% | — |

## Multimodal

- Gemini 3.1 Pro Preview: 38.1 (#60)
- Qwen3.7 Plus: 41.2 (#30)

| Benchmark | Gemini 3.1 Pro Preview | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1296 | 1281 |
| LMArena Document | 1444 | 1444 |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |

## Multilingual

- Gemini 3.1 Pro Preview: 57.1 (#11)
- Qwen3.7 Plus: 55.0 (#36)

| Benchmark | Gemini 3.1 Pro Preview | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1475 | 1445 |
| LMArena Chinese | 1528 | 1510 |
| LMArena French | 1488 | 1471 |
| LMArena German | 1491 | 1471 |
| LMArena Japanese | 1494 | 1411 |
| LMArena Korean | 1458 | 1416 |
| LMArena Russian | 1496 | 1457 |
| LMArena Spanish | 1480 | 1453 |

## Instruction Following

- Gemini 3.1 Pro Preview: 77.1 (#31)
- Qwen3.7 Plus: 75.9 (#49)

| Benchmark | Gemini 3.1 Pro Preview | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1465 | 1439 |

## Long Context

- Gemini 3.1 Pro Preview: 47.3 (#17)
- Qwen3.7 Plus: 44.5 (#61)

| Benchmark | Gemini 3.1 Pro Preview | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1482 | 1454 |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |

## Writing & Preference

- Gemini 3.1 Pro Preview: 66.3 (#36)
- Qwen3.7 Plus: 64.5 (#54)

| Benchmark | Gemini 3.1 Pro Preview | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1480 | 1454 |
| LMArena Creative Writing | 1482 | 1439 |
| LMArena Multi-Turn | 1486 | 1459 |
| EQ-Bench Creative Writing | 1491 | — |
| EQ-Bench 4 | 1142 | — |

## FAQ

### Is Gemini 3.1 Pro Preview better than Qwen3.7 Plus?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 45.0 on the Noometry Index. Qwen3.7 Plus costs 6.4× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.1 Pro Preview or Qwen3.7 Plus?

Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

### Is Gemini 3.1 Pro Preview or Qwen3.7 Plus better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.7 versus 36.1 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 1M.

### How many benchmarks do Gemini 3.1 Pro Preview and Qwen3.7 Plus share?

30 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Qwen3.7 Plus has 32.