# Gemini 1.5 Flash 8B vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.8 to 29.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-1-5-flash-8b-vs-qwen3-8-max
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Gemini 1.5 Flash 8B scores higher in 0 categories and Qwen3.8 Max in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 14.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.6% for Gemini 1.5 Flash 8B and 100% for Qwen3.8 Max.

## Snapshot

| | Gemini 1.5 Flash 8B | Qwen3.8 Max |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 29.9 | 56.8 |
| Rank | 301 | 22 |
| Context | — | 1M |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 1.5 Flash 8B: 35.5 (#225)
- Qwen3.8 Max: 53.5 (#29)

| Benchmark | Gemini 1.5 Flash 8B | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1218 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |

## Agentic & Tool Use

- Gemini 1.5 Flash 8B: —
- Qwen3.8 Max: 45.4 (#14)

| Benchmark | Gemini 1.5 Flash 8B | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |

## Reasoning

- Gemini 1.5 Flash 8B: 20.0 (#244)
- Qwen3.8 Max: 54.4 (#26)

| Benchmark | Gemini 1.5 Flash 8B | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 1209 | 1496 |
| DTBench | 50% | 92% |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.41 |

## Math

- Gemini 1.5 Flash 8B: 14.2 (#302)
- Qwen3.8 Max: 73.2 (#20)

| Benchmark | Gemini 1.5 Flash 8B | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.6% | 100% |
| LMArena Math | 1207 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |

## Knowledge

- Gemini 1.5 Flash 8B: 16.0 (#289)
- Qwen3.8 Max: 61.7 (#27)

| Benchmark | Gemini 1.5 Flash 8B | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 33% | 92.7% |
| LMArena Expert | 1185 | 1507 |
| SimpleQA Verified | — | 47.3% |

## Multimodal

- Gemini 1.5 Flash 8B: 28.2 (#115)
- Qwen3.8 Max: 37.2 (#75)

| Benchmark | Gemini 1.5 Flash 8B | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | 1044 | 1314 |
| Furniture Assembly | — | 20% |

## Multilingual

- Gemini 1.5 Flash 8B: 38.5 (#229)
- Qwen3.8 Max: 56.7 (#18)

| Benchmark | Gemini 1.5 Flash 8B | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1215 | 1472 |
| LMArena Chinese | 1231 | 1538 |
| LMArena French | 1234 | 1503 |
| LMArena German | 1206 | 1483 |
| LMArena Japanese | 1150 | 1467 |
| LMArena Korean | 1140 | 1461 |
| LMArena Russian | 1236 | 1481 |
| LMArena Spanish | 1212 | 1492 |

## Instruction Following

- Gemini 1.5 Flash 8B: 62.8 (#236)
- Qwen3.8 Max: 77.6 (#17)

| Benchmark | Gemini 1.5 Flash 8B | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1199 | 1479 |

## Long Context

- Gemini 1.5 Flash 8B: 37.0 (#225)
- Qwen3.8 Max: 45.6 (#31)

| Benchmark | Gemini 1.5 Flash 8B | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1219 | 1489 |

## Writing & Preference

- Gemini 1.5 Flash 8B: 42.8 (#232)
- Qwen3.8 Max: 67.1 (#30)

| Benchmark | Gemini 1.5 Flash 8B | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1226 | 1483 |
| LMArena Creative Writing | 1218 | 1479 |
| LMArena Multi-Turn | 1185 | 1489 |

## FAQ

### Is Gemini 1.5 Flash 8B better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 29.9 on the Noometry Index.

### Is Gemini 1.5 Flash 8B or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 35.5 in the Noometry coding category.

### How many benchmarks do Gemini 1.5 Flash 8B and Qwen3.8 Max share?

21 benchmarks have published results for both models. Gemini 1.5 Flash 8B has 21 scored results on Noometry and Qwen3.8 Max has 39.