Model comparison
Qwen2.5 7B Instruct vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 28.6 on the Noometry Index. Qwen2.5 7B Instruct costs 3.7× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. Qwen2.5 7B Instruct scores higher in 0 categories and Qwen3.6 Plus in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 17.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Qwen2.5 7B Instruct and 93.3% for Qwen3.6 Plus.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $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.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5 7B Instruct | Qwen3.6 Plus | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 28.6 | 47.3 |
| Released | 2024-09 | 2026-03-31 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.17 | $0.50 |
| Output $ / M tokens | $0.70 | $3 |
| Results tracked | 15 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Plus leads
Qwen2.5 7B Instruct: 35.9 (#204), Qwen3.6 Plus: 40.6 (#125)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.6 Plus |
|---|---|---|
| SWE-bench Verified | — | 57.9% |
| LMArena WebDev | — | 1461 |
| SciCode | — | 40.7% |
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1467 |
| BigCodeBench Complete | 46.1% | — |
| ALE-Bench | — | 670.15 |
Agentic & Tool Use Not comparable
Qwen2.5 7B Instruct: 23.5 (#117), Qwen3.6 Plus: —
| Benchmark | Qwen2.5 7B Instruct | Qwen3.6 Plus |
|---|---|---|
| BALROG | 7.8% | — |
| Vending-Bench 2 | — | 5,115 |
Reasoning Qwen3.6 Plus leads
Qwen2.5 7B Instruct: 14.3 (#317), Qwen3.6 Plus: 28.5 (#89)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.6 Plus |
|---|---|---|
| Chess Puzzles | 0% | 17% |
| DTBench | 47.7% | 81.9% |
| LMCA | 6.4% | 33.1% |
| Epoch Capabilities Index | 118.44 | 147.67 |
| NYT Connections (extended) | — | 60.3% |
| CritPt | — | 2.9% |
| Thematic Generalization | — | 59.5% |
| LMArena Hard Prompts | — | 1449 |
| Mystery Game Puzzles | — | 12% |
Math Qwen3.6 Plus leads
Qwen2.5 7B Instruct: 11.8 (#300), Qwen3.6 Plus: 50.6 (#44)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.6 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 93.3% |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| Omni-MATH | 29.4% | — |
| LMArena Math | — | 1450 |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Qwen3.6 Plus leads
Qwen2.5 7B Instruct: 17.0 (#281), Qwen3.6 Plus: 56.1 (#40)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 35.5% | 88.4% |
| SimpleQA Verified | — | 44.1% |
| MMLU-Pro | 53.9% | — |
| GPQA (HELM) | 34.1% | — |
| LMArena Expert | — | 1456 |
| MMLU | 72.9% | — |
Multilingual Not comparable
Qwen2.5 7B Instruct: —, Qwen3.6 Plus: 53.5 (#66)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.6 Plus |
|---|---|---|
| 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 Qwen3.6 Plus leads
Qwen2.5 7B Instruct: 63.4 (#226), Qwen3.6 Plus: 75.2 (#70)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.6 Plus |
|---|---|---|
| IFEval | 74.1% | — |
| LMArena Instruction Following | — | 1425 |
Long Context Not comparable
Qwen2.5 7B Instruct: —, Qwen3.6 Plus: 45.1 (#48)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.6 Plus |
|---|---|---|
| CL-bench | — | 20.3% |
| LMArena Longer Query | — | 1440 |
Writing & Preference Qwen3.6 Plus leads
Qwen2.5 7B Instruct: 48.8 (#194), Qwen3.6 Plus: 62.4 (#78)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | — | 1437 |
| LMArena Creative Writing | — | 1405 |
| WildBench | 73.1% | — |
| LMArena Multi-Turn | — | 1438 |
Frequently asked questions
Is Qwen2.5 7B Instruct better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 28.6 on the Noometry Index. Qwen2.5 7B Instruct costs 3.7× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Which is cheaper, Qwen2.5 7B Instruct or Qwen3.6 Plus?
Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is Qwen2.5 7B Instruct or Qwen3.6 Plus better for coding?
Qwen3.6 Plus scores higher on coding benchmarks: 40.6 versus 35.9 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 131K.
How many benchmarks do Qwen2.5 7B Instruct and Qwen3.6 Plus share?
6 benchmarks have published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and Qwen3.6 Plus has 37.