Model comparison
o4-mini vs Qwen3.5 27B
o4-mini and Qwen3.5 27B score almost the same on the Noometry Index (41.6 vs 41.9), so choose on price, context window or the category you care about most.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. o4-mini scores higher in 6 categories and Qwen3.5 27B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o4-mini leads 43.6 to 38.0.
- The biggest single-benchmark swing is WeirdML: 52.6% for o4-mini and 39.5% for Qwen3.5 27B.
- Qwen3.5 27B is cheaper at $0.30 / $2.40 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- Qwen3.5 27B accepts more context: 262K tokens versus 200K.
- Qwen3.5 27B has downloadable open weights; the other is API-only.
Side by side
| o4-mini | Qwen3.5 27B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.6 | 41.9 |
| Released | 2025-04-16 | 2026-02-23 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 100K | 66K |
| Input $ / M tokens | $1.10 | $0.30 |
| Output $ / M tokens | $4.40 | $2.40 |
| Results tracked | 60 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
o4-mini: 40.9 (#127), Qwen3.5 27B: 38.9 (#168)
| Benchmark | o4-mini | Qwen3.5 27B |
|---|---|---|
| WeirdML | 52.6% | 39.5% |
| LMArena Coding | 1368 | 1427 |
| ALE-Bench | 826.17 | 349.45 |
| SWE-bench Verified (bash only) | 45% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1358 |
| GSO | 3.6% | — |
| CadEval | 62% | — |
| AlgoTune | 1.72 | — |
Agentic & Tool Use Not comparable
o4-mini: 32.6 (#61), Qwen3.5 27B: —
| Benchmark | o4-mini | Qwen3.5 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 53.2% | — |
| GDPval | 25.3% | — |
| METR Time Horizons | 63.9% | — |
| Vending-Bench 2 | — | 201.98 |
Reasoning Qwen3.5 27B leads
o4-mini: 24.6 (#162), Qwen3.5 27B: 27.5 (#117)
| Benchmark | o4-mini | Qwen3.5 27B |
|---|---|---|
| LMArena Hard Prompts | 1351 | 1414 |
| DTBench | 77.6% | 82.4% |
| LMCA | 26.5% | 34% |
| ARC-AGI-2 | 6.1% | — |
| SimpleBench | 38.7% | — |
| Kagi LLM Benchmark | 67.6% | — |
| NYT Connections (extended) | — | 47.9% |
| ARC-AGI-1 | 58.7% | — |
| CritPt | 0.6% | — |
| Chess Puzzles | 26% | — |
| EnigmaEval | 9.2% | — |
| Thematic Generalization | — | 45.5% |
| Mystery Game Puzzles | 5% | — |
| Epoch Capabilities Index | 145.64 | — |
| ForecastBench | 61.8 | — |
Math o4-mini leads
o4-mini: 40.8 (#89), Qwen3.5 27B: 38.8 (#127)
| Benchmark | o4-mini | Qwen3.5 27B |
|---|---|---|
| LMArena Math | 1389 | 1429 |
| FrontierMath (Tiers 1-3) | 36.1% | — |
| FrontierMath Tier 4 | 4.9% | — |
| MathArena Final-Answer Competitions | — | 56.7% |
| OTIS Mock AIME 2024-2025 | 81.7% | — |
| Omni-MATH | 72% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 24.8% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge o4-mini leads
o4-mini: 43.6 (#91), Qwen3.5 27B: 38.0 (#150)
| Benchmark | o4-mini | Qwen3.5 27B |
|---|---|---|
| Vectara Hallucination Rate | 18.6% | 12.1% |
| LMArena Expert | 1343 | 1428 |
| GPQA Diamond | 79.6% | — |
| Humanity's Last Exam | 18.1% | — |
| SimpleQA Verified | 19.6% | — |
| MMLU-Pro | 82% | — |
| Confabulations | 15.8% | — |
| GPQA (HELM) | 73.5% | — |
Multimodal Too close to call
o4-mini: 40.2 (#49), Qwen3.5 27B: 39.4 (#59)
| Benchmark | o4-mini | Qwen3.5 27B |
|---|---|---|
| LMArena Vision | 1194 | 1241 |
| GeoBench | 64% | — |
| VPCT | 57.5% | — |
Multilingual Qwen3.5 27B leads
o4-mini: 47.0 (#154), Qwen3.5 27B: 50.8 (#115)
| Benchmark | o4-mini | Qwen3.5 27B |
|---|---|---|
| LMArena Non-English | 1337 | 1390 |
| LMArena Chinese | 1354 | 1478 |
| LMArena French | 1364 | 1410 |
| LMArena German | 1336 | 1393 |
| LMArena Japanese | 1308 | 1345 |
| LMArena Korean | 1312 | 1358 |
| LMArena Russian | 1334 | 1390 |
| LMArena Spanish | 1347 | 1407 |
Instruction Following o4-mini leads
o4-mini: 75.2 (#68), Qwen3.5 27B: 73.5 (#119)
| Benchmark | o4-mini | Qwen3.5 27B |
|---|---|---|
| LMArena Instruction Following | 1321 | 1393 |
| IFEval | 92.8% | — |
Long Context o4-mini leads
o4-mini: 45.5 (#33), Qwen3.5 27B: 43.1 (#106)
| Benchmark | o4-mini | Qwen3.5 27B |
|---|---|---|
| LMArena Longer Query | 1315 | 1413 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Qwen3.5 27B leads
o4-mini: 54.0 (#152), Qwen3.5 27B: 59.3 (#111)
| Benchmark | o4-mini | Qwen3.5 27B |
|---|---|---|
| LMArena Text | 1353 | 1409 |
| LMArena Creative Writing | 1294 | 1362 |
| LMArena Multi-Turn | 1350 | 1410 |
| Short-Story Creative Writing | 75% | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is o4-mini better than Qwen3.5 27B?
o4-mini and Qwen3.5 27B score almost the same on the Noometry Index (41.6 vs 41.9), so choose on price, context window or the category you care about most.
Which is cheaper, o4-mini or Qwen3.5 27B?
Qwen3.5 27B is cheaper. It lists at $0.30 per million input tokens and $2.40 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is o4-mini or Qwen3.5 27B better for coding?
o4-mini scores higher on coding benchmarks: 40.9 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 27B does, with 262K tokens against 200K.
How many benchmarks do o4-mini and Qwen3.5 27B share?
23 benchmarks have published results for both models. o4-mini has 60 scored results on Noometry and Qwen3.5 27B has 28.