# Gemini 3.6 Flash vs Qwen3 235B-A22B

> Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 43.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-6-flash-vs-qwen3-235b-a22b
- Last updated: 2026-10-10
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 7 categories and Qwen3 235B-A22B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.8 to 15.7.
- The biggest single-benchmark swing is ARC-AGI-1: 91.2% for Gemini 3.6 Flash and 11% for Qwen3 235B-A22B.
- Qwen3 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.6 Flash.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 131K.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.6 Flash | Qwen3 235B-A22B |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 54.1 | 43.5 |
| Rank | 33 | 91 |
| Context | 1.05M | 131K |
| Input $/M | $0.75 | $0.70 |
| Output $/M | $3.75 | $2.80 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.6 Flash: 50.0 (#48)
- Qwen3 235B-A22B: 44.3 (#75)

| Benchmark | Gemini 3.6 Flash | Qwen3 235B-A22B |
|---|---|---|
| SciCode | 52.7% | 42.4% |
| WeirdML | 56.1% | 41% |
| LMArena Coding | 1491 | 1445 |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| Aider Polyglot | — | 59.6% |
| LMArena WebDev | 1538 | — |
| ALE-Bench | 715.52 | — |

## Agentic & Tool Use

- Gemini 3.6 Flash: 32.3 (#65)
- Qwen3 235B-A22B: 33.9 (#51)

| Benchmark | Gemini 3.6 Flash | Qwen3 235B-A22B |
|---|---|---|
| APEX-Agents | 46.9% | — |
| Berkeley Function Calling Leaderboard | — | 52.1% |
| GDP.pdf | 14% | — |
| Vending-Bench 2 | — | -11.34 |

## Reasoning

- Gemini 3.6 Flash: 58.8 (#22)
- Qwen3 235B-A22B: 15.7 (#311)

| Benchmark | Gemini 3.6 Flash | Qwen3 235B-A22B |
|---|---|---|
| ARC-AGI-2 | 60.4% | 1.3% |
| ARC-AGI-1 | 91.2% | 11% |
| CritPt | 10.6% | 0% |
| Chess Puzzles | 43% | 12% |
| LMArena Hard Prompts | 1485 | 1433 |
| Mystery Game Puzzles | 30% | 9% |
| DTBench | 95.5% | 80.3% |
| LMCA | 44.9% | 29.3% |
| Epoch Capabilities Index | 154.25 | 143.85 |
| SimpleBench | — | 31% |
| Kagi LLM Benchmark | — | 69.4% |
| NYT Connections (extended) | 89% | — |
| ForecastBench | — | 59.7 |

## Math

- Gemini 3.6 Flash: 57.3 (#40)
- Qwen3 235B-A22B: 50.4 (#57)

| Benchmark | Gemini 3.6 Flash | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.2% | 86.7% |
| LMArena Math | 1505 | 1432 |
| FrontierMath (Tiers 1-3) | 58.9% | — |
| FrontierMath Tier 4 | 22% | — |
| MathArena Final-Answer Competitions | 70.8% | — |
| ProofBench | 36% | — |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Gemini 3.6 Flash: 67.8 (#8)
- Qwen3 235B-A22B: 49.6 (#73)

| Benchmark | Gemini 3.6 Flash | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 94.1% | 80.1% |
| SimpleQA Verified | 66.2% | 40.4% |
| LMArena Expert | 1488 | 1463 |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |

## Multimodal

- Gemini 3.6 Flash: 38.5 (#64)
- Qwen3 235B-A22B: —

| Benchmark | Gemini 3.6 Flash | Qwen3 235B-A22B |
|---|---|---|
| LMArena Vision | 1298 | — |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |
| LMArena Document | 1456 | — |

## Multilingual

- Gemini 3.6 Flash: 56.5 (#19)
- Qwen3 235B-A22B: 52.3 (#89)

| Benchmark | Gemini 3.6 Flash | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1469 | 1409 |
| LMArena Chinese | 1531 | 1481 |
| LMArena French | 1504 | 1445 |
| LMArena German | 1478 | 1433 |
| LMArena Japanese | 1476 | 1399 |
| LMArena Korean | 1431 | 1391 |
| LMArena Russian | 1487 | 1411 |
| LMArena Spanish | 1475 | 1430 |

## Instruction Following

- Gemini 3.6 Flash: 77.0 (#33)
- Qwen3 235B-A22B: 72.6 (#136)

| Benchmark | Gemini 3.6 Flash | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1466 | 1408 |
| IFEval | — | 83.5% |

## Long Context

- Gemini 3.6 Flash: 45.1 (#50)
- Qwen3 235B-A22B: 46.1 (#26)

| Benchmark | Gemini 3.6 Flash | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1474 | 1426 |
| Fiction.LiveBench | — | 75% |

## Writing & Preference

- Gemini 3.6 Flash: 68.2 (#27)
- Qwen3 235B-A22B: 59.6 (#108)

| Benchmark | Gemini 3.6 Flash | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1479 | 1419 |
| LMArena Creative Writing | 1465 | 1384 |
| EQ-Bench Creative Writing | 1604 | 1366 |
| LMArena Multi-Turn | 1481 | 1432 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 86.6% |

## FAQ

### Is Gemini 3.6 Flash better than Qwen3 235B-A22B?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 43.5 on the Noometry Index.

### Which is cheaper, Gemini 3.6 Flash or Qwen3 235B-A22B?

Qwen3 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Gemini 3.6 Flash lists at $0.75 and $3.75.

### Is Gemini 3.6 Flash or Qwen3 235B-A22B better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 44.3 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.6 Flash does, with 1.05M tokens against 131K.

### How many benchmarks do Gemini 3.6 Flash and Qwen3 235B-A22B share?

31 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and Qwen3 235B-A22B has 49.