Model comparison
Gemini 3.8 Flash vs Qwen2.5-Max
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 40.7 on the Noometry Index.
Last verified . 18 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 8 categories and Qwen2.5-Max 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 25.6.
Side by side
| Gemini 3.8 Flash | Qwen2.5-Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 61.8 | 40.7 |
| Released | 2026-09-02 | 2025-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.75 | — |
| Output $ / M tokens | $3.75 | — |
| Results tracked | 50 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.8 Flash leads
Gemini 3.8 Flash: 59.2 (#15), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Gemini 3.8 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1510 | 1359 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| CursorBench | 39.6% | — |
| LMArena WebDev | 1584 | — |
| FrontierSWE | 19.6% | — |
| SciCode | 56.6% | — |
| WeirdML | 84.8% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 1,270 | — |
Agentic & Tool Use Not comparable
Gemini 3.8 Flash: 41.8 (#21), Qwen2.5-Max: —
| Benchmark | Gemini 3.8 Flash | Qwen2.5-Max |
|---|---|---|
| APEX-Agents | 64.3% | — |
| Remote Labor Index | 5.8% | — |
| GDP.pdf | 23.4% | — |
| Vending-Bench 2 | 5,094 | — |
Reasoning Gemini 3.8 Flash leads
Gemini 3.8 Flash: 76.9 (#5), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Gemini 3.8 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1508 | 1360 |
| Epoch Capabilities Index | 156.71 | 132.53 |
| ARC-AGI-2 | 89.2% | — |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 18.3% | — |
| Chess Puzzles | 61% | — |
| LiveBench Reasoning | — | 51.4% |
| Mystery Game Puzzles | 47% | — |
| DTBench | 95.7% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 52.9% | — |
| Surface Evolver Bench | 76.9% | — |
| LiveBench | — | 62.3% |
Math Gemini 3.8 Flash leads
Gemini 3.8 Flash: 65.3 (#28), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Gemini 3.8 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1528 | 1369 |
| FrontierMath (Tiers 1-3) | 68.4% | — |
| FrontierMath Tier 4 | 22% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| ProofBench | 48% | — |
| LiveBench Math | — | 58.4% |
Knowledge Gemini 3.8 Flash leads
Gemini 3.8 Flash: 74.8 (#2), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Gemini 3.8 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1524 | 1337 |
| GPQA Diamond | 95.4% | — |
| Humanity's Last Exam | 44.5% | — |
| SimpleQA Verified | 69.7% | — |
| Confabulations | — | 21.8% |
Multimodal Not comparable
Gemini 3.8 Flash: 40.7 (#45), Qwen2.5-Max: —
| Benchmark | Gemini 3.8 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1314 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |
Multilingual Gemini 3.8 Flash leads
Gemini 3.8 Flash: 58.0 (#5), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Gemini 3.8 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1491 | 1352 |
| LMArena Chinese | 1554 | 1382 |
| LMArena French | 1498 | 1396 |
| LMArena German | 1493 | 1350 |
| LMArena Japanese | 1502 | 1300 |
| LMArena Korean | 1459 | 1304 |
| LMArena Russian | 1515 | 1353 |
| LMArena Spanish | 1485 | 1377 |
Instruction Following Gemini 3.8 Flash leads
Gemini 3.8 Flash: 78.0 (#13), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Gemini 3.8 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1490 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Gemini 3.8 Flash leads
Gemini 3.8 Flash: 46.3 (#24), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Gemini 3.8 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1508 | 1358 |
Writing & Preference Gemini 3.8 Flash leads
Gemini 3.8 Flash: 72.2 (#15), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Gemini 3.8 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1499 | 1367 |
| LMArena Creative Writing | 1492 | 1339 |
| LMArena Multi-Turn | 1501 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 1748 | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Gemini 3.8 Flash better than Qwen2.5-Max?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 40.7 on the Noometry Index.
Is Gemini 3.8 Flash or Qwen2.5-Max better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 41.8 in the Noometry coding category.
How many benchmarks do Gemini 3.8 Flash and Qwen2.5-Max share?
18 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and Qwen2.5-Max has 27.