# Gemini 3.8 Flash vs Qwen3.5-Flash

> Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 42.5 on the Noometry Index. Qwen3.5-Flash costs 8.6× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-8-flash-vs-qwen3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 8 categories and Qwen3.5-Flash in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 33.7.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 68.4% for Gemini 3.8 Flash and 18.2% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Gemini 3.8 Flash | Qwen3.5-Flash |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 61.8 | 42.5 |
| Rank | 11 | 112 |
| Context | 1.05M | 1M |
| Input $/M | $0.75 | $0.10 |
| Output $/M | $3.75 | $0.40 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.8 Flash: 59.2 (#15)
- Qwen3.5-Flash: 34.2 (#242)

| Benchmark | Gemini 3.8 Flash | Qwen3.5-Flash |
|---|---|---|
| LMArena WebDev | 1584 | 1244 |
| LMArena Coding | 1510 | 1412 |
| ALE-Bench | 1,270 | 221.8 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| CursorBench | 39.6% | — |
| FrontierSWE | 19.6% | — |
| SciCode | 56.6% | — |
| WeirdML | 84.8% | — |

## Agentic & Tool Use

- Gemini 3.8 Flash: 41.8 (#21)
- Qwen3.5-Flash: —

| Benchmark | Gemini 3.8 Flash | Qwen3.5-Flash |
|---|---|---|
| Vending-Bench 2 | 5,094 | 462.69 |
| APEX-Agents | 64.3% | — |
| Remote Labor Index | 5.8% | — |
| GDP.pdf | 23.4% | — |

## Reasoning

- Gemini 3.8 Flash: 76.9 (#5)
- Qwen3.5-Flash: 33.7 (#72)

| Benchmark | Gemini 3.8 Flash | Qwen3.5-Flash |
|---|---|---|
| Chess Puzzles | 61% | 21% |
| LMArena Hard Prompts | 1508 | 1403 |
| Mystery Game Puzzles | 47% | 20% |
| DTBench | 95.7% | 82.9% |
| LMCA | 52.9% | 29.1% |
| Epoch Capabilities Index | 156.71 | 143.98 |
| ARC-AGI-2 | 89.2% | — |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 18.3% | — |
| Surface Evolver Bench | 76.9% | — |

## Math

- Gemini 3.8 Flash: 65.3 (#28)
- Qwen3.5-Flash: 37.4 (#158)

| Benchmark | Gemini 3.8 Flash | Qwen3.5-Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 68.4% | 18.2% |
| OTIS Mock AIME 2024-2025 | 98.9% | 84.4% |
| LMArena Math | 1528 | 1407 |
| FrontierMath Tier 4 | 22% | — |
| ProofBench | 48% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Gemini 3.8 Flash: 74.8 (#2)
- Qwen3.5-Flash: 43.2 (#93)

| Benchmark | Gemini 3.8 Flash | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 95.4% | 82.3% |
| SimpleQA Verified | 69.7% | 20.3% |
| LMArena Expert | 1524 | 1407 |
| Humanity's Last Exam | 44.5% | — |
| Vectara Hallucination Rate | — | 10.5% |

## Multimodal

- Gemini 3.8 Flash: 40.7 (#45)
- Qwen3.5-Flash: —

| Benchmark | Gemini 3.8 Flash | Qwen3.5-Flash |
|---|---|---|
| LMArena Vision | 1314 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |

## Multilingual

- Gemini 3.8 Flash: 58.0 (#5)
- Qwen3.5-Flash: 50.5 (#121)

| Benchmark | Gemini 3.8 Flash | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1491 | 1385 |
| LMArena Chinese | 1554 | 1446 |
| LMArena French | 1498 | 1412 |
| LMArena German | 1493 | 1390 |
| LMArena Japanese | 1502 | 1368 |
| LMArena Korean | 1459 | 1344 |
| LMArena Russian | 1515 | 1379 |
| LMArena Spanish | 1485 | 1400 |

## Instruction Following

- Gemini 3.8 Flash: 78.0 (#13)
- Qwen3.5-Flash: 72.6 (#139)

| Benchmark | Gemini 3.8 Flash | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1490 | 1374 |

## Long Context

- Gemini 3.8 Flash: 46.3 (#24)
- Qwen3.5-Flash: 42.4 (#124)

| Benchmark | Gemini 3.8 Flash | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1508 | 1392 |

## Writing & Preference

- Gemini 3.8 Flash: 72.2 (#15)
- Qwen3.5-Flash: 57.9 (#122)

| Benchmark | Gemini 3.8 Flash | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1499 | 1397 |
| LMArena Creative Writing | 1492 | 1343 |
| LMArena Multi-Turn | 1501 | 1393 |
| EQ-Bench Creative Writing | 1748 | — |

## FAQ

### Is Gemini 3.8 Flash better than Qwen3.5-Flash?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 42.5 on the Noometry Index. Qwen3.5-Flash costs 8.6× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.8 Flash or Qwen3.5-Flash?

Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.

### Is Gemini 3.8 Flash or Qwen3.5-Flash better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 34.2 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 1M.

### How many benchmarks do Gemini 3.8 Flash and Qwen3.5-Flash share?

29 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and Qwen3.5-Flash has 32.