Model comparison
Gemini 3.7 Flash vs Qwen3.8 Max
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 56.8 on the Noometry Index.
Last verified . 38 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 38 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 8 categories and Qwen3.8 Max in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.0 to 54.4.
- The biggest single-benchmark swing is SimpleQA Verified: 69.2% for Gemini 3.7 Flash and 47.3% for Qwen3.8 Max.
- Gemini 3.7 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Gemini 3.7 Flash accepts more context: 1.05M tokens versus 1M.
Side by side
| Gemini 3.7 Flash | Qwen3.8 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 59.8 | 56.8 |
| Released | 2026-08-13 | 2026-08-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.75 | $2 |
| Output $ / M tokens | $3.75 | $6 |
| Results tracked | 44 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.7 Flash leads
Gemini 3.7 Flash: 56.2 (#22), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Gemini 3.7 Flash | Qwen3.8 Max |
|---|---|---|
| DeepSWE | 65.5% | 57.5% |
| LMArena WebDev | 1592 | 1674 |
| FrontierSWE | 20.3% | 17.8% |
| SciCode | 59.8% | 53.2% |
| LMArena Coding | 1497 | 1502 |
| FrontierCode | 43.6% | — |
| ALE-Bench | 904.3 | — |
Agentic & Tool Use Qwen3.8 Max leads
Gemini 3.7 Flash: 42.1 (#19), Qwen3.8 Max: 45.4 (#14)
| Benchmark | Gemini 3.7 Flash | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | 67.8% | 63.3% |
| GDP.pdf | 23.8% | 23.2% |
| Remote Labor Index | 5% | — |
| τ²-bench Banking | — | 55.1% |
Reasoning Gemini 3.7 Flash leads
Gemini 3.7 Flash: 70.0 (#15), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Gemini 3.7 Flash | Qwen3.8 Max |
|---|---|---|
| NYT Connections (extended) | 94% | 88.3% |
| CritPt | 14.3% | 20% |
| Chess Puzzles | 47% | 40% |
| LMArena Hard Prompts | 1494 | 1496 |
| Mystery Game Puzzles | 37% | 38% |
| DTBench | 96.8% | 92% |
| LMCA | 50.4% | 46.2% |
| Epoch Capabilities Index | 157.27 | 156.41 |
| ARC-AGI-2 | 84.6% | — |
| ARC-AGI-1 | 95.5% | — |
Math Qwen3.8 Max leads
Gemini 3.7 Flash: 69.6 (#23), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Gemini 3.7 Flash | Qwen3.8 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 71.6% | 74.7% |
| FrontierMath Tier 4 | 36.6% | 46.3% |
| OTIS Mock AIME 2024-2025 | 97.2% | 100% |
| ProofBench | 58% | 58% |
| LMArena Math | 1507 | 1499 |
Knowledge Gemini 3.7 Flash leads
Gemini 3.7 Flash: 69.7 (#5), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Gemini 3.7 Flash | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 94.8% | 92.7% |
| SimpleQA Verified | 69.2% | 47.3% |
| LMArena Expert | 1508 | 1507 |
Multimodal Too close to call
Gemini 3.7 Flash: 37.3 (#73), Qwen3.8 Max: 37.2 (#75)
| Benchmark | Gemini 3.7 Flash | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | 1316 | 1314 |
| Furniture Assembly | 26.7% | 20% |
Multilingual Too close to call
Gemini 3.7 Flash: 57.6 (#7), Qwen3.8 Max: 56.7 (#18)
| Benchmark | Gemini 3.7 Flash | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1484 | 1472 |
| LMArena Chinese | 1548 | 1538 |
| LMArena French | 1505 | 1503 |
| LMArena German | 1498 | 1483 |
| LMArena Japanese | 1512 | 1467 |
| LMArena Korean | 1483 | 1461 |
| LMArena Russian | 1516 | 1481 |
| LMArena Spanish | 1503 | 1492 |
Instruction Following Too close to call
Gemini 3.7 Flash: 77.7 (#15), Qwen3.8 Max: 77.6 (#17)
| Benchmark | Gemini 3.7 Flash | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1483 | 1479 |
Long Context Too close to call
Gemini 3.7 Flash: 45.7 (#30), Qwen3.8 Max: 45.6 (#31)
| Benchmark | Gemini 3.7 Flash | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1492 | 1489 |
Writing & Preference Gemini 3.7 Flash leads
Gemini 3.7 Flash: 71.2 (#20), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Gemini 3.7 Flash | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1486 | 1483 |
| LMArena Creative Writing | 1490 | 1479 |
| LMArena Multi-Turn | 1489 | 1489 |
| EQ-Bench Creative Writing | 1723 | — |
Frequently asked questions
Is Gemini 3.7 Flash better than Qwen3.8 Max?
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 56.8 on the Noometry Index.
Which is cheaper, Gemini 3.7 Flash or Qwen3.8 Max?
Gemini 3.7 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is Gemini 3.7 Flash or Qwen3.8 Max better for coding?
Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 53.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.7 Flash does, with 1.05M tokens against 1M.
How many benchmarks do Gemini 3.7 Flash and Qwen3.8 Max share?
38 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and Qwen3.8 Max has 39.