Model comparison
Gemini 2.5 Flash-Lite vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 21× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 1 category and Qwen3.7 Max in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Max leads 61.7 to 32.1.
- The biggest single-benchmark swing is DTBench: 62.8% for Gemini 2.5 Flash-Lite and 92.3% for Qwen3.7 Max.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 1M.
Side by side
| Gemini 2.5 Flash-Lite | Qwen3.7 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 36.4 | 51.4 |
| Released | 2025-06-17 | 2026-05-19 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.10 | $2.50 |
| Output $ / M tokens | $0.40 | $7.50 |
| Results tracked | 33 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Gemini 2.5 Flash-Lite: 38.0 (#167), Qwen3.7 Max: 50.2 (#43)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3.7 Max |
|---|---|---|
| LMArena Coding | 1373 | 1498 |
| ALE-Bench | 325.9 | 1,189 |
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| WeirdML | 35.2% | — |
Agentic & Tool Use Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 27.8 (#89), Qwen3.7 Max: 21.8 (#129)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3.7 Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | — |
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
Gemini 2.5 Flash-Lite: 21.5 (#196), Qwen3.7 Max: 48.4 (#36)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3.7 Max |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1483 |
| DTBench | 62.8% | 92.3% |
| LMCA | 18.1% | 44% |
| Epoch Capabilities Index | 133.93 | 153.74 |
| SimpleBench | — | 70.4% |
| Kagi LLM Benchmark | 40.5% | — |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 13.4% |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
Math Qwen3.7 Max leads
Gemini 2.5 Flash-Lite: 35.5 (#144), Qwen3.7 Max: 62.3 (#26)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3.7 Max |
|---|---|---|
| LMArena Math | 1373 | 1488 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
| Omni-MATH | 48% | — |
Knowledge Qwen3.7 Max leads
Gemini 2.5 Flash-Lite: 32.1 (#206), Qwen3.7 Max: 61.7 (#24)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3.7 Max |
|---|---|---|
| LMArena Expert | 1373 | 1488 |
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 55.8% |
| MMLU-Pro | 53.7% | — |
| Vectara Hallucination Rate | 3.3% | — |
| GPQA (HELM) | 30.9% | — |
Multimodal Not comparable
Gemini 2.5 Flash-Lite: 28.6 (#109), Qwen3.7 Max: —
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3.7 Max |
|---|---|---|
| LMArena Vision | 1198 | — |
| VPCT | 30% | — |
Multilingual Qwen3.7 Max leads
Gemini 2.5 Flash-Lite: 49.5 (#129), Qwen3.7 Max: 57.1 (#13)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1369 | 1475 |
| LMArena Chinese | 1404 | 1533 |
| LMArena Russian | 1373 | 1482 |
| LMArena French | 1388 | — |
| LMArena German | 1390 | — |
| LMArena Japanese | 1359 | — |
| LMArena Korean | 1358 | — |
| LMArena Spanish | 1396 | — |
Instruction Following Qwen3.7 Max leads
Gemini 2.5 Flash-Lite: 70.2 (#163), Qwen3.7 Max: 76.9 (#34)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1366 | 1460 |
| IFEval | 81% | — |
Long Context Qwen3.7 Max leads
Gemini 2.5 Flash-Lite: 33.3 (#257), Qwen3.7 Max: 45.4 (#34)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1373 | 1484 |
| Fiction.LiveBench | 47.2% | — |
Writing & Preference Qwen3.7 Max leads
Gemini 2.5 Flash-Lite: 57.0 (#130), Qwen3.7 Max: 65.2 (#52)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1379 | 1476 |
| LMArena Creative Writing | 1366 | 1450 |
| LMArena Multi-Turn | 1367 | 1482 |
| WildBench | 81.8% | — |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 21× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash-Lite or Qwen3.7 Max?
Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is Gemini 2.5 Flash-Lite or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 38.0 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash-Lite does, with 1.05M tokens against 1M.
How many benchmarks do Gemini 2.5 Flash-Lite and Qwen3.7 Max share?
16 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Qwen3.7 Max has 33.