Compare / head-to-head
Qwen3 4B Instruct 2507vsQwen3-Coder 30B-A3B Instruct
Qwen3-Coder 30B-A3B Instruct leads 2 of 2 shared benchmarks. Both offer a 262K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 2
Qwen3-Coder 30B-A3B Instruct leads
Cheaper per token
—
list price, input + output
Larger context
Tie
both 262K tokens
Providers
Qwen
same provider
Qwen3 4B Instruct 2507
Qwen · released 2025-08-06
text
- Context
- 262K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 18 · 7 core
Qwen3-Coder 30B-A3B Instruct
Qwen · released 2025-07-31
text
Quality
Benchmark matrix
2 shared · 16 only Qwen3 4B Instruct 2507 · 11 only Qwen3-Coder 30B-A3B Instruct| Benchmark | Qwen3 4B Instruct 2507 | Qwen3-Coder 30B-A3B Instruct | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| Aider-Polyglot | 12.9% ↗ | 33.3% ↗ | -20.4 pt | Qwen3-Coder 30B-A3B Instruct |
| BFCL-v3 | 61.9% ↗ | 62.2% ↗ | -0.3 pt | Qwen3-Coder 30B-A3B Instruct |
| Only Qwen3 4B Instruct 2507 reports · 16 | ||||
| GPQA Diamond | 45.8% ↗epoch run | not reported | — | — |
| MMLU-Pro | 69.6% ↗ | not reported | — | — |
| AIME25 | 47.4% ↗ | not reported | — | — |
| Arena-Hard v2 | 43.4% ↗ | not reported | — | — |
| Chess Puzzles (Epoch AI run) | 4% ↗epoch run | not reported | — | — |
| GPQA | 62% ↗ | not reported | — | — |
| HMMT25 | 31% ↗ | not reported | — | — |
| IFEval | 83.4% ↗ | not reported | — | — |
| LiveBench 20241125 | 63% ↗ | not reported | — | — |
| LiveCodeBench v6 (25.02-25.05) | 35.1% ↗ | not reported | — | — |
| MMLU-Redux | 84.2% ↗ | not reported | — | — |
| MultiPL-E | 76.8% ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 52.2% ↗epoch run | not reported | — | — |
| SuperGPQA | 42.8% ↗ | not reported | — | — |
| TAU2-Retail | 40.4% ↗ | not reported | — | — |
| ZebraLogic | 80.2% ↗ | not reported | — | — |
| Only Qwen3-Coder 30B-A3B Instruct reports · 11 | ||||
| Mind2Web | not reported | 51% ↗ | — | — |
| Multi-SWE-bench flash | not reported | 19.3% ↗ | — | — |
| Multi-SWE-bench mini | not reported | 19.5% ↗ | — | — |
| Spider2 | not reported | 21.4% ↗ | — | — |
| SWE-bench Live | not reported | 20.7% ↗ | — | — |
| SWE-bench Multilingual | not reported | 34.7% ↗ | — | — |
| SWE-bench Verified (w/ OpenHands, 500 turns) | not reported | 51.6% ↗ | — | — |
| TAU-Bench Airline | not reported | 48% ↗ | — | — |
| TAU-Bench Retail | not reported | 68.7% ↗ | — | — |
| Terminal-Bench | not reported | 31.3% ↗ | — | — |
| WebArena | not reported | 43.5% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Qwen3 4B Instruct 2507 minus Qwen3-Coder 30B-A3B Instruct in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Qwen3 4B Instruct 2507 | Qwen3-Coder 30B-A3B Instruct | Edge |
|---|---|---|---|
| Context window | 262K tokens | 262K tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | — | $0.45 ↗ | — |
| Output price / 1M | — | $2.25 ↗ | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $2.7 | — |
| Modalities | text | text | Tie |
| Released | 2025-08-06 | 2025-07-31 | — |
| Cited benchmark scores | 18 | 13 | — |
Reliability
Qwen status
Live from /statusMore matchups
Qwen3 4B Instruct 2507 vs …
Models sharing the most benchmarksMore matchups
Qwen3-Coder 30B-A3B Instruct vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Qwen3 4B Instruct 2507 and Qwen3-Coder 30B-A3B Instruct on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.