Model comparison
GPT-4o mini vs Qwen3.5-Flash
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 25.5 on the Noometry Index.
Last verified . 26 shared benchmarks.
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and Qwen3.5-Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5-Flash leads 37.4 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.9% for GPT-4o mini and 84.4% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.15 / $0.60 for GPT-4o mini.
- Qwen3.5-Flash accepts more context: 1M tokens versus 128K.
Side by side
| GPT-4o mini | Qwen3.5-Flash | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 25.5 | 42.5 |
| Released | 2024-07-18 | 2026-02-23 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 1M |
| Max output | 16K | 66K |
| Input $ / M tokens | $0.15 | $0.10 |
| Output $ / M tokens | $0.60 | $0.40 |
| Results tracked | 60 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5-Flash leads
GPT-4o mini: 22.0 (#335), Qwen3.5-Flash: 34.2 (#242)
| Benchmark | GPT-4o mini | Qwen3.5-Flash |
|---|---|---|
| LMArena Coding | 1290 | 1412 |
| Aider Polyglot | 3.6% | — |
| LMArena WebDev | — | 1244 |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 221.8 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Not comparable
GPT-4o mini: 27.5 (#101), Qwen3.5-Flash: —
| Benchmark | GPT-4o mini | Qwen3.5-Flash |
|---|---|---|
| BALROG | 17.4% | — |
| Vending-Bench 2 | — | 462.69 |
Reasoning Qwen3.5-Flash leads
GPT-4o mini: 8.7 (#347), Qwen3.5-Flash: 33.7 (#72)
| Benchmark | GPT-4o mini | Qwen3.5-Flash |
|---|---|---|
| Chess Puzzles | 0% | 21% |
| LMArena Hard Prompts | 1267 | 1403 |
| Mystery Game Puzzles | 12% | 20% |
| DTBench | 54.4% | 82.9% |
| LMCA | 10.4% | 29.1% |
| Epoch Capabilities Index | 126.56 | 143.98 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| LiveBench Reasoning | 32.8% | — |
| LiveBench Data Analysis | 50% | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math Qwen3.5-Flash leads
GPT-4o mini: 10.4 (#314), Qwen3.5-Flash: 37.4 (#158)
| Benchmark | GPT-4o mini | Qwen3.5-Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | 18.2% |
| OTIS Mock AIME 2024-2025 | 6.9% | 84.4% |
| LMArena Math | 1267 | 1407 |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| MATH Level 5 | 52.6% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |
| GSM8K | 91.3% | — |
Knowledge Qwen3.5-Flash leads
GPT-4o mini: 17.7 (#284), Qwen3.5-Flash: 43.2 (#93)
| Benchmark | GPT-4o mini | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 37.7% | 82.3% |
| SimpleQA Verified | 8.3% | 20.3% |
| LMArena Expert | 1235 | 1407 |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| Vectara Hallucination Rate | — | 10.5% |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Not comparable
GPT-4o mini: 25.9 (#122), Qwen3.5-Flash: —
| Benchmark | GPT-4o mini | Qwen3.5-Flash |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual Qwen3.5-Flash leads
GPT-4o mini: 42.0 (#199), Qwen3.5-Flash: 50.5 (#121)
| Benchmark | GPT-4o mini | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1266 | 1385 |
| LMArena Chinese | 1265 | 1446 |
| LMArena French | 1297 | 1412 |
| LMArena German | 1272 | 1390 |
| LMArena Japanese | 1216 | 1368 |
| LMArena Korean | 1195 | 1344 |
| LMArena Russian | 1275 | 1379 |
| LMArena Spanish | 1276 | 1400 |
Instruction Following Qwen3.5-Flash leads
GPT-4o mini: 61.9 (#239), Qwen3.5-Flash: 72.6 (#139)
| Benchmark | GPT-4o mini | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1258 | 1374 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |
Long Context Qwen3.5-Flash leads
GPT-4o mini: 39.1 (#186), Qwen3.5-Flash: 42.4 (#124)
| Benchmark | GPT-4o mini | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1289 | 1392 |
Writing & Preference Qwen3.5-Flash leads
GPT-4o mini: 39.5 (#248), Qwen3.5-Flash: 57.9 (#122)
| Benchmark | GPT-4o mini | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1286 | 1397 |
| LMArena Creative Writing | 1268 | 1343 |
| LMArena Multi-Turn | 1285 | 1393 |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than Qwen3.5-Flash?
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 25.5 on the Noometry Index.
Which is cheaper, GPT-4o mini or Qwen3.5-Flash?
Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; GPT-4o mini lists at $0.15 and $0.60.
Is GPT-4o mini or Qwen3.5-Flash better for coding?
Qwen3.5-Flash scores higher on coding benchmarks: 34.2 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5-Flash does, with 1M tokens against 128K.
How many benchmarks do GPT-4o mini and Qwen3.5-Flash share?
26 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Qwen3.5-Flash has 32.