Model comparison
Qwen3.6 Plus vs Qwen3 8B
Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 33.3 on the Noometry Index. Qwen3 8B costs 3.6× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Last verified . 8 shared benchmarks.
Alibaba (Qwen)Summary
- They share 8 benchmarks with published results for both. Qwen3.6 Plus scores higher in 5 categories and Qwen3 8B in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 36.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for Qwen3.6 Plus and 56.1% for Qwen3 8B.
- Qwen3 8B is cheaper at $0.18 / $0.70 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- Qwen3.6 Plus accepts more context: 1M tokens versus 131K.
- Qwen3 8B has downloadable open weights; the other is API-only.
Side by side
| Qwen3.6 Plus | Qwen3 8B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 47.3 | 33.3 |
| Released | 2026-03-31 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 1M | 131K |
| Max output | 66K | 8K |
| Input $ / M tokens | $0.50 | $0.18 |
| Output $ / M tokens | $3 | $0.70 |
| Results tracked | 37 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Plus leads
Qwen3.6 Plus: 40.6 (#125), Qwen3 8B: 33.4 (#245)
| Benchmark | Qwen3.6 Plus | Qwen3 8B |
|---|---|---|
| SciCode | 40.7% | 22.6% |
| SWE-bench Verified | 57.9% | — |
| LMArena WebDev | 1461 | — |
| LMArena Coding | 1467 | — |
| ALE-Bench | 670.15 | — |
Agentic & Tool Use Not comparable
Qwen3.6 Plus: —, Qwen3 8B: 29.9 (#71)
| Benchmark | Qwen3.6 Plus | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |
| Vending-Bench 2 | 5,115 | — |
Reasoning Qwen3.6 Plus leads
Qwen3.6 Plus: 28.5 (#89), Qwen3 8B: 16.1 (#299)
| Benchmark | Qwen3.6 Plus | Qwen3 8B |
|---|---|---|
| CritPt | 2.9% | 0% |
| Chess Puzzles | 17% | 5% |
| DTBench | 81.9% | 59.7% |
| LMCA | 33.1% | 8.8% |
| Epoch Capabilities Index | 147.67 | 136.17 |
| NYT Connections (extended) | 60.3% | — |
| Thematic Generalization | 59.5% | — |
| LMArena Hard Prompts | 1449 | — |
| Mystery Game Puzzles | 12% | — |
Math Qwen3.6 Plus leads
Qwen3.6 Plus: 50.6 (#44), Qwen3 8B: 33.3 (#176)
| Benchmark | Qwen3.6 Plus | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 56.1% |
| FrontierMath (Tiers 1-3) | 38.2% | — |
| LMArena Math | 1450 | — |
| FrontierMath (Feb 2025 set) | 26.2% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
Knowledge Qwen3.6 Plus leads
Qwen3.6 Plus: 56.1 (#40), Qwen3 8B: 36.1 (#164)
| Benchmark | Qwen3.6 Plus | Qwen3 8B |
|---|---|---|
| GPQA Diamond | 88.4% | 56.8% |
| SimpleQA Verified | 44.1% | — |
| Vectara Hallucination Rate | — | 4.8% |
| LMArena Expert | 1456 | — |
Multilingual Not comparable
Qwen3.6 Plus: 53.5 (#66), Qwen3 8B: —
| Benchmark | Qwen3.6 Plus | Qwen3 8B |
|---|---|---|
| LMArena Non-English | 1424 | — |
| LMArena Chinese | 1478 | — |
| LMArena French | 1454 | — |
| LMArena German | 1451 | — |
| LMArena Japanese | 1389 | — |
| LMArena Korean | 1381 | — |
| LMArena Russian | 1434 | — |
| LMArena Spanish | 1432 | — |
Instruction Following Not comparable
Qwen3.6 Plus: 75.2 (#70), Qwen3 8B: —
| Benchmark | Qwen3.6 Plus | Qwen3 8B |
|---|---|---|
| LMArena Instruction Following | 1425 | — |
Long Context Qwen3.6 Plus leads
Qwen3.6 Plus: 45.1 (#48), Qwen3 8B: 37.8 (#205)
| Benchmark | Qwen3.6 Plus | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
| CL-bench | 20.3% | — |
| LMArena Longer Query | 1440 | — |
Writing & Preference Not comparable
Qwen3.6 Plus: 62.4 (#78), Qwen3 8B: —
| Benchmark | Qwen3.6 Plus | Qwen3 8B |
|---|---|---|
| LMArena Text | 1437 | — |
| LMArena Creative Writing | 1405 | — |
| LMArena Multi-Turn | 1438 | — |
Frequently asked questions
Is Qwen3.6 Plus better than Qwen3 8B?
Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 33.3 on the Noometry Index. Qwen3 8B costs 3.6× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Which is cheaper, Qwen3.6 Plus or Qwen3 8B?
Qwen3 8B is cheaper. It lists at $0.18 per million input tokens and $0.70 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is Qwen3.6 Plus or Qwen3 8B better for coding?
Qwen3.6 Plus scores higher on coding benchmarks: 40.6 versus 33.4 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 131K.
How many benchmarks do Qwen3.6 Plus and Qwen3 8B share?
8 benchmarks have published results for both models. Qwen3.6 Plus has 37 scored results on Noometry and Qwen3 8B has 11.