Model comparison
o4-mini vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 41.6 on the Noometry Index.
Last verified . 30 shared benchmarks.
Alibaba (Qwen)Summary
- They share 30 benchmarks with published results for both. o4-mini scores higher in 3 categories and Qwen3.6 Plus in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 43.6.
- The biggest single-benchmark swing is SimpleQA Verified: 19.6% for o4-mini and 44.1% for Qwen3.6 Plus.
- Qwen3.6 Plus is cheaper at $0.50 / $3 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- Qwen3.6 Plus accepts more context: 1M tokens versus 200K.
Side by side
| o4-mini | Qwen3.6 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.6 | 47.5 |
| Released | 2025-04-16 | 2026-03-31 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1M |
| Max output | 100K | 66K |
| Input $ / M tokens | $1.10 | $0.50 |
| Output $ / M tokens | $4.40 | $3 |
| Results tracked | 60 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
o4-mini: 40.9 (#127), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | o4-mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Coding | 1368 | 1467 |
| ALE-Bench | 826.17 | 670.15 |
| SWE-bench Verified | — | 57.9% |
| SWE-bench Verified (bash only) | 45% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1461 |
| SciCode | — | 40.7% |
| GSO | 3.6% | — |
| WeirdML | 52.6% | — |
| CadEval | 62% | — |
| AlgoTune | 1.72 | — |
Agentic & Tool Use Not comparable
o4-mini: 32.6 (#61), Qwen3.6 Plus: —
| Benchmark | o4-mini | Qwen3.6 Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 53.2% | — |
| GDPval | 25.3% | — |
| METR Time Horizons | 63.9% | — |
| Vending-Bench 2 | — | 5,115 |
Reasoning Qwen3.6 Plus leads
o4-mini: 24.6 (#162), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | o4-mini | Qwen3.6 Plus |
|---|---|---|
| CritPt | 0.6% | 2.9% |
| Chess Puzzles | 26% | 17% |
| LMArena Hard Prompts | 1351 | 1449 |
| Mystery Game Puzzles | 5% | 12% |
| DTBench | 77.6% | 81.9% |
| LMCA | 26.5% | 33.1% |
| Epoch Capabilities Index | 145.64 | 147.65 |
| ARC-AGI-2 | 6.1% | — |
| SimpleBench | 38.7% | — |
| Kagi LLM Benchmark | 67.6% | — |
| NYT Connections (extended) | — | 60.3% |
| ARC-AGI-1 | 58.7% | — |
| EnigmaEval | 9.2% | — |
| Thematic Generalization | — | 59.5% |
| ForecastBench | 61.8 | — |
Math Qwen3.6 Plus leads
o4-mini: 40.8 (#89), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | o4-mini | Qwen3.6 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.1% | 38.2% |
| OTIS Mock AIME 2024-2025 | 81.7% | 93.3% |
| LMArena Math | 1389 | 1450 |
| FrontierMath (Feb 2025 set) | 24.8% | 26.2% |
| FrontierMath Tier 4 (v1) | 6.3% | 8.3% |
| FrontierMath Tier 4 | 4.9% | — |
| Omni-MATH | 72% | — |
| MATH Level 5 | 97.8% | — |
Knowledge Qwen3.6 Plus leads
o4-mini: 43.6 (#91), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | o4-mini | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 79.6% | 88.4% |
| SimpleQA Verified | 19.6% | 44.1% |
| LMArena Expert | 1343 | 1454 |
| Humanity's Last Exam | 18.1% | — |
| MMLU-Pro | 82% | — |
| Confabulations | 15.8% | — |
| Vectara Hallucination Rate | 18.6% | — |
| GPQA (HELM) | 73.5% | — |
Multimodal Not comparable
o4-mini: 40.2 (#49), Qwen3.6 Plus: —
| Benchmark | o4-mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1194 | — |
| GeoBench | 64% | — |
| VPCT | 57.5% | — |
Multilingual Qwen3.6 Plus leads
o4-mini: 47.0 (#154), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | o4-mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1337 | 1424 |
| LMArena Chinese | 1354 | 1477 |
| LMArena French | 1364 | 1455 |
| LMArena German | 1336 | 1452 |
| LMArena Japanese | 1308 | 1389 |
| LMArena Korean | 1312 | 1379 |
| LMArena Russian | 1334 | 1434 |
| LMArena Spanish | 1347 | 1432 |
Instruction Following Too close to call
o4-mini: 75.2 (#68), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | o4-mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1321 | 1425 |
| IFEval | 92.8% | — |
Long Context Too close to call
o4-mini: 45.5 (#33), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | o4-mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1315 | 1439 |
| Fiction.LiveBench | 77.8% | — |
| CL-bench | — | 20.3% |
Writing & Preference Qwen3.6 Plus leads
o4-mini: 54.0 (#152), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | o4-mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1353 | 1437 |
| LMArena Creative Writing | 1294 | 1404 |
| LMArena Multi-Turn | 1350 | 1438 |
| Short-Story Creative Writing | 75% | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is o4-mini better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 41.6 on the Noometry Index.
Which is cheaper, o4-mini or Qwen3.6 Plus?
Qwen3.6 Plus is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is o4-mini or Qwen3.6 Plus better for coding?
They score almost the same on coding (40.9 vs 40.8); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 200K.
How many benchmarks do o4-mini and Qwen3.6 Plus share?
30 benchmarks have published results for both models. o4-mini has 60 scored results on Noometry and Qwen3.6 Plus has 37.