Model comparison
Gemini 2.5 Flash-Lite vs Qwen3-1.7B
Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 26.2 on the Noometry Index.
Last verified . 1 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Gemini 2.5 Flash-Lite scores higher in 4 categories and Qwen3-1.7B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.5 Flash-Lite leads 35.5 to 15.4.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 36.9% for Gemini 2.5 Flash-Lite and 28.4% for Qwen3-1.7B.
- Qwen3-1.7B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash-Lite | Qwen3-1.7B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 36.4 | 26.2 |
| Released | 2025-06-17 | 2025-04-29 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 33 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemini 2.5 Flash-Lite: 38.0 (#167), Qwen3-1.7B: —
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-1.7B |
|---|---|---|
| WeirdML | 35.2% | — |
| LMArena Coding | 1373 | — |
| ALE-Bench | 325.9 | — |
Agentic & Tool Use Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 27.8 (#89), Qwen3-1.7B: 24.5 (#108)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-1.7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | 28.4% |
Reasoning Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 21.5 (#196), Qwen3-1.7B: 18.5 (#263)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-1.7B |
|---|---|---|
| Kagi LLM Benchmark | 40.5% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1377 | — |
| DTBench | 62.8% | — |
| LMCA | 18.1% | — |
| Epoch Capabilities Index | 133.93 | — |
Math Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 35.5 (#144), Qwen3-1.7B: 15.4 (#288)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-1.7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | 48% | — |
| LMArena Math | 1373 | — |
Knowledge Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 32.1 (#206), Qwen3-1.7B: 19.6 (#273)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-1.7B |
|---|---|---|
| GPQA Diamond | — | 38% |
| MMLU-Pro | 53.7% | — |
| Vectara Hallucination Rate | 3.3% | — |
| GPQA (HELM) | 30.9% | — |
| LMArena Expert | 1373 | — |
Multimodal Not comparable
Gemini 2.5 Flash-Lite: 28.6 (#109), Qwen3-1.7B: —
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-1.7B |
|---|---|---|
| LMArena Vision | 1198 | — |
| VPCT | 30% | — |
Multilingual Not comparable
Gemini 2.5 Flash-Lite: 49.5 (#129), Qwen3-1.7B: —
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-1.7B |
|---|---|---|
| LMArena Non-English | 1369 | — |
| LMArena Chinese | 1404 | — |
| LMArena French | 1388 | — |
| LMArena German | 1390 | — |
| LMArena Japanese | 1359 | — |
| LMArena Korean | 1358 | — |
| LMArena Russian | 1373 | — |
| LMArena Spanish | 1396 | — |
Instruction Following Not comparable
Gemini 2.5 Flash-Lite: 70.2 (#163), Qwen3-1.7B: —
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-1.7B |
|---|---|---|
| IFEval | 81% | — |
| LMArena Instruction Following | 1366 | — |
Long Context Not comparable
Gemini 2.5 Flash-Lite: 33.3 (#257), Qwen3-1.7B: —
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-1.7B |
|---|---|---|
| Fiction.LiveBench | 47.2% | — |
| LMArena Longer Query | 1373 | — |
Writing & Preference Not comparable
Gemini 2.5 Flash-Lite: 57.0 (#130), Qwen3-1.7B: —
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-1.7B |
|---|---|---|
| LMArena Text | 1379 | — |
| LMArena Creative Writing | 1366 | — |
| WildBench | 81.8% | — |
| LMArena Multi-Turn | 1367 | — |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than Qwen3-1.7B?
Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 26.2 on the Noometry Index.
How many benchmarks do Gemini 2.5 Flash-Lite and Qwen3-1.7B share?
1 benchmark has published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Qwen3-1.7B has 4.