Compare / head-to-head
MiniMax M2.5vsQwen3.7-Max
MiniMax M2.5 and Qwen3.7-Max do not yet share a public benchmark, so quality cannot be compared apples-to-apples. MiniMax M2.5 is 4.4x cheaper per token. Qwen3.7-Max has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0
no overlap yet
Cheaper per token
MiniMax M2.5
4.4x cheaper, input + output
Larger context
Qwen3.7-Max
1M tokens
Provider uptime (30d)
100% · —
MiniMax · Qwen
MiniMax M2.5
MiniMax · released 2026-02-12
text
Qwen3.7-Max
Qwen · released 2026-05-20
textvision
Quality
Benchmark matrix
0 shared · 1 only MiniMax M2.5 · 0 only Qwen3.7-Max| Benchmark | MiniMax M2.5 | Qwen3.7-Max | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 0 | ||||
| No public benchmark is reported for both models yet. | ||||
| Only MiniMax M2.5 reports · 1 | ||||
| LMArena Elo | 1358.9 ↗ | not reported | — | — |
| Only Qwen3.7-Max reports · 0 | ||||
| Qwen3.7-Max reports nothing MiniMax M2.5 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 MiniMax M2.5 minus Qwen3.7-Max 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 M2.5 | Qwen3.7-Max | Edge |
|---|---|---|---|
| Context window | 205K tokens | 1M tokens | Qwen3.7-Max |
| Max output | — | — | — |
| Input price / 1M | $0.3 ↗ | $1.65 ↗ | MiniMax M2.5 |
| Output price / 1M | $1.2 ↗ | $4.95 ↗ | MiniMax M2.5 |
| Cached input / 1M | $0.03 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.5 | $6.6 | MiniMax M2.5 |
| Modalities | text | text · vision | Qwen3.7-Max |
| Released | 2026-02-12 | 2026-05-20 | — |
| Cited benchmark scores | 1 | 0 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
MiniMax M2.5 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run MiniMax M2.5 and Qwen3.7-Max on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.