# Qwen2.5 7B Instruct vs Qwen3 8B

> Qwen3 8B is the stronger model overall, scoring 33.3 to 28.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-5-7b-instruct-vs-qwen3-8b
- Last updated: 2026-10-10
- Shared benchmarks: 6

## 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 33.3 to 11.8.
- 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.

## Snapshot

| | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 28.6 | 33.3 |
| Rank | 314 | 237 |
| Context | 131K | 131K |
| Input $/M | $0.17 | $0.18 |
| Output $/M | $0.70 | $0.70 |
| Weights | Open | Open |

## Coding

- Qwen2.5 7B Instruct: 35.9 (#204)
- Qwen3 8B: 33.4 (#245)

| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| SciCode | — | 22.6% |
| BigCodeBench Instruct | 37.6% | — |
| BigCodeBench Complete | 46.1% | — |

## Agentic & Tool Use

- Qwen2.5 7B Instruct: 23.5 (#117)
- Qwen3 8B: 29.9 (#71)

| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |
| BALROG | 7.8% | — |

## Reasoning

- Qwen2.5 7B Instruct: 14.3 (#317)
- Qwen3 8B: 16.1 (#299)

| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| Chess Puzzles | 0% | 5% |
| DTBench | 47.7% | 59.7% |
| LMCA | 6.4% | 8.8% |
| Epoch Capabilities Index | 118.44 | 136.17 |
| CritPt | — | 0% |

## Math

- Qwen2.5 7B Instruct: 11.8 (#300)
- Qwen3 8B: 33.3 (#176)

| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 56.1% |
| Omni-MATH | 29.4% | — |

## Knowledge

- Qwen2.5 7B Instruct: 17.0 (#281)
- Qwen3 8B: 36.1 (#164)

| 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

- Qwen2.5 7B Instruct: 63.4 (#226)
- Qwen3 8B: —

| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| IFEval | 74.1% | — |

## Long Context

- Qwen2.5 7B Instruct: —
- Qwen3 8B: 37.8 (#205)

| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |

## Writing & Preference

- Qwen2.5 7B Instruct: 48.8 (#194)
- Qwen3 8B: —

| Benchmark | Qwen2.5 7B Instruct | Qwen3 8B |
|---|---|---|
| WildBench | 73.1% | — |

## FAQ

### Is Qwen2.5 7B Instruct better than Qwen3 8B?

Qwen3 8B is the stronger model overall, scoring 33.3 to 28.6 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: 35.9 versus 33.4 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.