Compare / head-to-head
Qwen3 30B-A3B Instruct 2507vsQwen3 4B Instruct 2507
Qwen3 30B-A3B Instruct 2507 leads 17 of 18 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
17 – 1
Qwen3 30B-A3B Instruct 2507 leads
Cheaper per token
—
list price, input + output
Larger context
Tie
both 262K tokens
Providers
Qwen
same provider
Qwen3 30B-A3B Instruct 2507
Qwen · released 2025-07-30
text
Qwen3 4B Instruct 2507
Qwen · released 2025-08-06
text
- Context
- 262K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 18 · 7 core
Quality
Benchmark matrix
18 shared · 1 only Qwen3 30B-A3B Instruct 2507 · 0 only Qwen3 4B Instruct 2507| Benchmark | Qwen3 30B-A3B Instruct 2507 | Qwen3 4B Instruct 2507 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 18 | ||||
| GPQA Diamond | 55.6% ↗epoch run | 45.8% ↗epoch run | +9.8 pt | Qwen3 30B-A3B Instruct 2507 |
| MMLU-Pro | 78.4% ↗ | 69.6% ↗ | +8.8 pt | Qwen3 30B-A3B Instruct 2507 |
| Aider-Polyglot | 35.6% ↗ | 12.9% ↗ | +22.7 pt | Qwen3 30B-A3B Instruct 2507 |
| AIME25 | 61.3% ↗ | 47.4% ↗ | +13.9 pt | Qwen3 30B-A3B Instruct 2507 |
| Arena-Hard v2 | 69% ↗ | 43.4% ↗ | +25.6 pt | Qwen3 30B-A3B Instruct 2507 |
| BFCL-v3 | 65.1% ↗ | 61.9% ↗ | +3.2 pt | Qwen3 30B-A3B Instruct 2507 |
| Chess Puzzles (Epoch AI run) | 2% ↗epoch run | 4% ↗epoch run | -2 pt | Qwen3 4B Instruct 2507 |
| GPQA | 70.4% ↗ | 62% ↗ | +8.4 pt | Qwen3 30B-A3B Instruct 2507 |
| HMMT25 | 43% ↗ | 31% ↗ | +12 pt | Qwen3 30B-A3B Instruct 2507 |
| IFEval | 84.7% ↗ | 83.4% ↗ | +1.3 pt | Qwen3 30B-A3B Instruct 2507 |
| LiveBench 20241125 | 69% ↗ | 63% ↗ | +6 pt | Qwen3 30B-A3B Instruct 2507 |
| LiveCodeBench v6 (25.02-25.05) | 43.2% ↗ | 35.1% ↗ | +8.1 pt | Qwen3 30B-A3B Instruct 2507 |
| MMLU-Redux | 89.3% ↗ | 84.2% ↗ | +5.1 pt | Qwen3 30B-A3B Instruct 2507 |
| MultiPL-E | 83.8% ↗ | 76.8% ↗ | +7 pt | Qwen3 30B-A3B Instruct 2507 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 62.2% ↗epoch run | 52.2% ↗epoch run | +10 pt | Qwen3 30B-A3B Instruct 2507 |
| SuperGPQA | 53.4% ↗ | 42.8% ↗ | +10.6 pt | Qwen3 30B-A3B Instruct 2507 |
| TAU2-Retail | 57% ↗ | 40.4% ↗ | +16.6 pt | Qwen3 30B-A3B Instruct 2507 |
| ZebraLogic | 90% ↗ | 80.2% ↗ | +9.8 pt | Qwen3 30B-A3B Instruct 2507 |
| Only Qwen3 30B-A3B Instruct 2507 reports · 1 | ||||
| LMArena Elo | 1382.7 ↗ | not reported | — | — |
| Only Qwen3 4B Instruct 2507 reports · 0 | ||||
| Qwen3 4B Instruct 2507 reports nothing Qwen3 30B-A3B Instruct 2507 does not. | ||||
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 30B-A3B Instruct 2507 minus Qwen3 4B Instruct 2507 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 30B-A3B Instruct 2507 | Qwen3 4B Instruct 2507 | Edge |
|---|---|---|---|
| Context window | 262K tokens | 262K tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | $0.2 ↗ | — | — |
| Output price / 1M | $0.8 ↗ | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1 | — | — |
| Modalities | text | text | Tie |
| Released | 2025-07-30 | 2025-08-06 | — |
| Cited benchmark scores | 19 | 18 | — |
Reliability
Qwen status
Live from /statusMore matchups
Qwen3 30B-A3B Instruct 2507 vs …
Models sharing the most benchmarksMore matchups
Qwen3 4B Instruct 2507 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Qwen3 30B-A3B Instruct 2507 and Qwen3 4B Instruct 2507 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.