Model comparison
Gemini 3.8 Flash vs Qwen3 235B-A22B
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 43.5 on the Noometry Index.
Last verified . 32 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 32 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 9 categories and Qwen3 235B-A22B 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 15.7.
- The biggest single-benchmark swing is ARC-AGI-2: 89.2% for Gemini 3.8 Flash and 1.3% 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 3.8 Flash.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 131K.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.8 Flash | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 61.8 | 43.5 |
| Released | 2026-09-02 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 66K | 16K |
| Input $ / M tokens | $0.75 | $0.70 |
| Output $ / M tokens | $3.75 | $2.80 |
| Results tracked | 50 | 49 |
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), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | Gemini 3.8 Flash | Qwen3 235B-A22B |
|---|---|---|
| SciCode | 56.6% | 42.4% |
| WeirdML | 84.8% | 41% |
| LMArena Coding | 1510 | 1445 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| Aider Polyglot | — | 59.6% |
| CursorBench | 39.6% | — |
| LMArena WebDev | 1584 | — |
| FrontierSWE | 19.6% | — |
| ALE-Bench | 1,270 | — |
Agentic & Tool Use Gemini 3.8 Flash leads
Gemini 3.8 Flash: 41.8 (#21), Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | Gemini 3.8 Flash | Qwen3 235B-A22B |
|---|---|---|
| Vending-Bench 2 | 5,094 | -11.34 |
| APEX-Agents | 64.3% | — |
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Remote Labor Index | 5.8% | — |
| GDP.pdf | 23.4% | — |
Reasoning Gemini 3.8 Flash leads
Gemini 3.8 Flash: 76.9 (#5), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | Gemini 3.8 Flash | Qwen3 235B-A22B |
|---|---|---|
| ARC-AGI-2 | 89.2% | 1.3% |
| ARC-AGI-1 | 98.5% | 11% |
| CritPt | 18.3% | 0% |
| Chess Puzzles | 61% | 12% |
| LMArena Hard Prompts | 1508 | 1433 |
| Mystery Game Puzzles | 47% | 9% |
| DTBench | 95.7% | 80.3% |
| LMCA | 52.9% | 29.3% |
| Epoch Capabilities Index | 156.71 | 143.85 |
| SimpleBench | — | 31% |
| Kagi LLM Benchmark | — | 69.4% |
| NYT Connections (extended) | 97.4% | — |
| Surface Evolver Bench | 76.9% | — |
| ForecastBench | — | 59.7 |
Math Gemini 3.8 Flash leads
Gemini 3.8 Flash: 65.3 (#28), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | Gemini 3.8 Flash | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.9% | 86.7% |
| LMArena Math | 1528 | 1432 |
| FrontierMath (Tiers 1-3) | 68.4% | — |
| FrontierMath Tier 4 | 22% | — |
| ProofBench | 48% | — |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Gemini 3.8 Flash leads
Gemini 3.8 Flash: 74.8 (#2), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | Gemini 3.8 Flash | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 95.4% | 80.1% |
| SimpleQA Verified | 69.7% | 40.4% |
| LMArena Expert | 1524 | 1463 |
| Humanity's Last Exam | 44.5% | — |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |
Multimodal Not comparable
Gemini 3.8 Flash: 40.7 (#45), Qwen3 235B-A22B: —
| Benchmark | Gemini 3.8 Flash | Qwen3 235B-A22B |
|---|---|---|
| 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), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | Gemini 3.8 Flash | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1491 | 1409 |
| LMArena Chinese | 1554 | 1481 |
| LMArena French | 1498 | 1445 |
| LMArena German | 1493 | 1433 |
| LMArena Japanese | 1502 | 1399 |
| LMArena Korean | 1459 | 1391 |
| LMArena Russian | 1515 | 1411 |
| LMArena Spanish | 1485 | 1430 |
Instruction Following Gemini 3.8 Flash leads
Gemini 3.8 Flash: 78.0 (#13), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | Gemini 3.8 Flash | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1490 | 1408 |
| IFEval | — | 83.5% |
Long Context Too close to call
Gemini 3.8 Flash: 46.3 (#24), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | Gemini 3.8 Flash | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1508 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Gemini 3.8 Flash leads
Gemini 3.8 Flash: 72.2 (#15), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | Gemini 3.8 Flash | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1499 | 1419 |
| LMArena Creative Writing | 1492 | 1384 |
| EQ-Bench Creative Writing | 1748 | 1366 |
| LMArena Multi-Turn | 1501 | 1432 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 86.6% |
Frequently asked questions
Is Gemini 3.8 Flash better than Qwen3 235B-A22B?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 43.5 on the Noometry Index.
Which is cheaper, Gemini 3.8 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 3.8 Flash lists at $0.75 and $3.75.
Is Gemini 3.8 Flash or Qwen3 235B-A22B better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 44.3 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.8 Flash does, with 1.05M tokens against 131K.
How many benchmarks do Gemini 3.8 Flash and Qwen3 235B-A22B share?
32 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and Qwen3 235B-A22B has 49.