Compare / head-to-head
MiniMax M2vs
Qwen3-Coder 30B-A3B Instruct
MiniMax M2 leads 2 of 2 shared benchmarks. MiniMax M2 is 1.8x cheaper per token. Qwen3-Coder 30B-A3B Instruct has the larger context window (262K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 0
MiniMax M2 leads
Cheaper per token
MiniMax M2
1.8x cheaper, input + output
Larger context
Qwen3-Coder 30B-A3B Instruct
262K tokens
Providers
2 providers
MiniMax · Qwen
MiniMax M2
MiniMax · released 2025-10-27
text
Qwen3-Coder 30B-A3B Instruct
Qwen · released 2025-07-31
text
Quality
Benchmark matrix
2 shared · 15 only MiniMax M2 · 11 only Qwen3-Coder 30B-A3B Instruct| Benchmark | MiniMax M2 | Qwen3-Coder 30B-A3B Instruct | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| SWE-bench Multilingual | 56.5% ↗ | 34.7% ↗ | +21.8 pt | MiniMax M2 |
| Terminal-Bench | 46.3% ↗ | 31.3% ↗ | +15 pt | MiniMax M2 |
| Only MiniMax M2 reports · 15 | ||||
| SWE-bench Verified | 69.4% ↗ | not reported | — | — |
| LMArena Elo | 1343.4 ↗ | not reported | — | — |
| AgentCompany | 36% ↗ | not reported | — | — |
| ArtifactsBench | 66.8% ↗ | not reported | — | — |
| BrowseComp | 44% ↗ | not reported | — | — |
| BrowseComp-zh | 48.5% ↗ | not reported | — | — |
| FinSearchComp-global | 65.5% ↗ | not reported | — | — |
| GAIA (text only) | 75.7% ↗ | not reported | — | — |
| HLE (w/ tools) | 31.8% ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1296.6 ↗ | not reported | — | — |
| Multi-SWE-Bench | 36.2% ↗ | not reported | — | — |
| SimpleBench (SimpleBench) | 25% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 160.6 ↗ | not reported | — | — |
| xbench-DeepSearch | 72% ↗ | not reported | — | — |
| τ²-Bench | 77.2% ↗ | not reported | — | — |
| Only Qwen3-Coder 30B-A3B Instruct reports · 11 | ||||
| Aider-Polyglot | not reported | 33.3% ↗ | — | — |
| BFCL-v3 | not reported | 62.2% ↗ | — | — |
| 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 Verified (w/ OpenHands, 500 turns) | not reported | 51.6% ↗ | — | — |
| TAU-Bench Airline | not reported | 48% ↗ | — | — |
| TAU-Bench Retail | not reported | 68.7% ↗ | — | — |
| 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 MiniMax M2 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 | MiniMax M2 | Qwen3-Coder 30B-A3B Instruct | Edge |
|---|---|---|---|
| Context window | 205K tokens | 262K tokens | Qwen3-Coder 30B-A3B Instruct |
| Max output | 128K tokens | — | — |
| Input price / 1M | $0.3 ↗ | $0.45 ↗ | MiniMax M2 |
| Output price / 1M | $1.2 ↗ | $2.25 ↗ | MiniMax M2 |
| Cached input / 1M | $0.03 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.5 | $2.7 | MiniMax M2 |
| Modalities | text | text | Tie |
| Released | 2025-10-27 | 2025-07-31 | — |
| Cited benchmark scores | 17 | 13 | — |
Reliability
Provider status
Live from /statusMore matchups
MiniMax M2 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 MiniMax M2 and Qwen3-Coder 30B-A3B Instruct on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.