Model comparison
GPT-5 Mini vs Qwen3.5 122B-A10B
GPT-5 Mini and Qwen3.5 122B-A10B score almost the same on the Noometry Index (41.8 vs 42.1), so choose on price, context window or the category you care about most.
Last verified . 24 shared benchmarks.
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. GPT-5 Mini scores higher in 4 categories and Qwen3.5 122B-A10B in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.7 to 39.1.
- The biggest single-benchmark swing is Mystery Game Puzzles: 10% for GPT-5 Mini and 17% for Qwen3.5 122B-A10B.
- GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $0.40 / $3.20 for Qwen3.5 122B-A10B.
- GPT-5 Mini accepts more context: 400K tokens versus 262K.
- Qwen3.5 122B-A10B has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Mini | Qwen3.5 122B-A10B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.8 | 42.1 |
| Released | 2025-08-07 | 2026-02-23 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.25 | $0.40 |
| Output $ / M tokens | $2 | $3.20 |
| Results tracked | 60 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Mini leads
GPT-5 Mini: 40.1 (#146), Qwen3.5 122B-A10B: 39.1 (#162)
| Benchmark | GPT-5 Mini | Qwen3.5 122B-A10B |
|---|---|---|
| SciCode | 39.2% | 35.6% |
| LMArena Coding | 1406 | 1436 |
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| LMArena WebDev | — | 1360 |
| SWE-bench Multilingual | 39.7% | — |
| WeirdML | 52.7% | — |
| ALE-Bench | 799.77 | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use Not comparable
GPT-5 Mini: 31.1 (#70), Qwen3.5 122B-A10B: —
| Benchmark | GPT-5 Mini | Qwen3.5 122B-A10B |
|---|---|---|
| Terminal-Bench | 34.8% | — |
| Berkeley Function Calling Leaderboard | 55.5% | — |
| Vending-Bench 2 | -31.18 | — |
Reasoning Qwen3.5 122B-A10B leads
GPT-5 Mini: 23.9 (#168), Qwen3.5 122B-A10B: 27.2 (#123)
| Benchmark | GPT-5 Mini | Qwen3.5 122B-A10B |
|---|---|---|
| CritPt | 0% | 0.9% |
| LMArena Hard Prompts | 1380 | 1421 |
| Mystery Game Puzzles | 10% | 17% |
| DTBench | 80.5% | 84.3% |
| LMCA | 34.2% | 32.2% |
| ARC-AGI-2 | 4.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| NYT Connections (extended) | — | 51.7% |
| ARC-AGI-1 | 54.3% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | 8.2% | — |
| Thematic Generalization | — | 51.2% |
| Epoch Capabilities Index | 145.52 | — |
| ForecastBench | 61 | — |
Math GPT-5 Mini leads
GPT-5 Mini: 46.7 (#69), Qwen3.5 122B-A10B: 39.1 (#112)
| Benchmark | GPT-5 Mini | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | 1378 | 1432 |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 9% | — |
| Omni-MATH | 72.2% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.6 (#86), Qwen3.5 122B-A10B: 38.8 (#142)
| Benchmark | GPT-5 Mini | Qwen3.5 122B-A10B |
|---|---|---|
| Vectara Hallucination Rate | 12.9% | 11.2% |
| LMArena Expert | 1379 | 1432 |
| GPQA Diamond | 75% | — |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| MMLU-Pro | 83.5% | — |
| Confabulations | 13.3% | — |
| GPQA (HELM) | 75.6% | — |
Multimodal Qwen3.5 122B-A10B leads
GPT-5 Mini: 35.6 (#85), Qwen3.5 122B-A10B: 39.6 (#57)
| Benchmark | GPT-5 Mini | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | 1202 | 1245 |
| VPCT | 40.2% | — |
Multilingual Qwen3.5 122B-A10B leads
GPT-5 Mini: 48.9 (#137), Qwen3.5 122B-A10B: 51.6 (#107)
| Benchmark | GPT-5 Mini | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | 1363 | 1400 |
| LMArena Chinese | 1385 | 1462 |
| LMArena French | 1386 | 1442 |
| LMArena German | 1366 | 1426 |
| LMArena Japanese | 1341 | 1367 |
| LMArena Korean | 1308 | 1352 |
| LMArena Russian | 1362 | 1400 |
| LMArena Spanish | 1355 | 1424 |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.2 (#46), Qwen3.5 122B-A10B: 73.8 (#115)
| Benchmark | GPT-5 Mini | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | 1357 | 1399 |
| IFEval | 92.7% | — |
Long Context Qwen3.5 122B-A10B leads
GPT-5 Mini: 41.9 (#132), Qwen3.5 122B-A10B: 43.0 (#109)
| Benchmark | GPT-5 Mini | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | 1355 | 1410 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference Qwen3.5 122B-A10B leads
GPT-5 Mini: 55.2 (#148), Qwen3.5 122B-A10B: 60.0 (#105)
| Benchmark | GPT-5 Mini | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | 1373 | 1417 |
| LMArena Creative Writing | 1325 | 1368 |
| LMArena Multi-Turn | 1363 | 1416 |
| Short-Story Creative Writing | 83.1% | — |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
Frequently asked questions
Is GPT-5 Mini better than Qwen3.5 122B-A10B?
GPT-5 Mini and Qwen3.5 122B-A10B score almost the same on the Noometry Index (41.8 vs 42.1), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-5 Mini or Qwen3.5 122B-A10B?
GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Qwen3.5 122B-A10B lists at $0.40 and $3.20.
Is GPT-5 Mini or Qwen3.5 122B-A10B better for coding?
GPT-5 Mini scores higher on coding benchmarks: 40.1 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Mini does, with 400K tokens against 262K.
How many benchmarks do GPT-5 Mini and Qwen3.5 122B-A10B share?
24 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Qwen3.5 122B-A10B has 27.