Model comparison
Qwen2.5 7B Instruct vs Qwen3 8B
Qwen3 8B is the stronger model overall, scoring 33.7 to 29.0 on the Noometry Index.
Last verified . 6 shared benchmarks.
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. Qwen2.5 7B Instruct scores higher in 1 category and Qwen3 8B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 8B leads 34.9 to 12.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Qwen2.5 7B Instruct and 56.1% for Qwen3 8B.
- Both cost about the same: $0.17 input and $0.70 output per million tokens.
Side by side
| Qwen2.5 7B Instruct | Qwen3 8B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 29.0 | 33.7 |
| Released | 2024-09 | 2025-04 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 8K | 8K |
| Input $ / M tokens | $0.17 | $0.18 |
| Output $ / M tokens | $0.70 | $0.70 |
| Results tracked | 15 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 7B Instruct leads
Qwen2.5 7B Instruct: 36.5 (#208), Qwen3 8B: 34.0 (#248)
| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| SciCode | — | 22.6% |
| BigCodeBench Instruct | 37.6% | — |
| BigCodeBench Complete | 46.1% | — |
Agentic & Tool Use Qwen3 8B leads
Qwen2.5 7B Instruct: 23.8 (#124), Qwen3 8B: 30.2 (#78)
| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |
| BALROG | 7.8% | — |
Reasoning Qwen3 8B leads
Qwen2.5 7B Instruct: 14.8 (#322), Qwen3 8B: 16.6 (#303)
| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| Chess Puzzles | 0% | 5% |
| DTBench | 47.7% | 59.7% |
| LMCA | 6.4% | 8.8% |
| Epoch Capabilities Index | 118.51 | 136.17 |
| CritPt | — | 0% |
Math Qwen3 8B leads
Qwen2.5 7B Instruct: 12.6 (#306), Qwen3 8B: 34.9 (#191)
| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 56.1% |
| Omni-MATH | 29.4% | — |
Knowledge Qwen3 8B leads
Qwen2.5 7B Instruct: 17.0 (#286), Qwen3 8B: 36.1 (#173)
| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| GPQA Diamond | 35.5% | 56.8% |
| MMLU-Pro | 53.9% | — |
| Vectara Hallucination Rate | — | 4.8% |
| GPQA (HELM) | 34.1% | — |
| MMLU | 72.9% | — |
Instruction Following Not comparable
Qwen2.5 7B Instruct: 63.2 (#231), Qwen3 8B: —
| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| IFEval | 74.1% | — |
Long Context Not comparable
Qwen2.5 7B Instruct: —, Qwen3 8B: 37.9 (#210)
| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
Writing & Preference Not comparable
Qwen2.5 7B Instruct: 48.8 (#195), Qwen3 8B: —
| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| WildBench | 73.1% | — |
Frequently asked questions
Is Qwen2.5 7B Instruct better than Qwen3 8B?
Qwen3 8B is the stronger model overall, scoring 33.7 to 29.0 on the Noometry Index.
Which is cheaper, Qwen2.5 7B Instruct or Qwen3 8B?
Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; Qwen3 8B lists at $0.18 and $0.70.
Is Qwen2.5 7B Instruct or Qwen3 8B better for coding?
Qwen2.5 7B Instruct scores higher on coding benchmarks: 36.5 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do Qwen2.5 7B Instruct and Qwen3 8B share?
6 benchmarks have published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and Qwen3 8B has 11.