# Qwen3-4B vs Qwen3 8B

> Qwen3 8B is the stronger model overall, scoring 33.3 to 31.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-4b-vs-qwen3-8b
- Last updated: 2026-10-10
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. Qwen3-4B scores higher in 1 category and Qwen3 8B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 8B leads 33.3 to 28.5.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 35.7% for Qwen3-4B and 42.6% for Qwen3 8B.

## Snapshot

| | Qwen3-4B | Qwen3 8B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 31.5 | 33.3 |
| Rank | 261 | 237 |
| Context | — | 131K |
| Input $/M | — | $0.18 |
| Output $/M | — | $0.70 |
| Weights | Open | Open |

## Coding

- Qwen3-4B: —
- Qwen3 8B: 33.4 (#245)

| Benchmark | Qwen3-4B | Qwen3 8B |
|---|---|---|
| SciCode | — | 22.6% |

## Agentic & Tool Use

- Qwen3-4B: 27.3 (#94)
- Qwen3 8B: 29.9 (#71)

| Benchmark | Qwen3-4B | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 35.7% | 42.6% |

## Reasoning

- Qwen3-4B: 18.5 (#264)
- Qwen3 8B: 16.1 (#299)

| Benchmark | Qwen3-4B | Qwen3 8B |
|---|---|---|
| Chess Puzzles | 4% | 5% |
| CritPt | — | 0% |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |
| Epoch Capabilities Index | — | 136.17 |

## Math

- Qwen3-4B: 28.5 (#228)
- Qwen3 8B: 33.3 (#176)

| Benchmark | Qwen3-4B | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 52.2% | 56.1% |
| MathArena Final-Answer Competitions | 38.5% | — |

## Knowledge

- Qwen3-4B: 33.0 (#198)
- Qwen3 8B: 36.1 (#164)

| Benchmark | Qwen3-4B | Qwen3 8B |
|---|---|---|
| GPQA Diamond | 52.3% | 56.8% |
| Vectara Hallucination Rate | 5.7% | 4.8% |

## Long Context

- Qwen3-4B: —
- Qwen3 8B: 37.8 (#205)

| Benchmark | Qwen3-4B | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |

## FAQ

### Is Qwen3-4B better than Qwen3 8B?

Qwen3 8B is the stronger model overall, scoring 33.3 to 31.5 on the Noometry Index.

### How many benchmarks do Qwen3-4B and Qwen3 8B share?

5 benchmarks have published results for both models. Qwen3-4B has 6 scored results on Noometry and Qwen3 8B has 11.
