MiniCPM5-1B vs Qwen3.7 Max: Benchmarks, Pricing & Capabilities Compared
TL;DR — MiniCPM5-1B wins for general use · Qwen3.7 Max wins for reasoning + long-context.
MiniCPM5-1B OpenBMB
- Released
- 2026-05-25
- Context window
- 128K tokens
- Input price
- $0.00 / Mtok
- Output price
- $0.00 / Mtok
Qwen3.7 Max Alibaba
- Released
- 2026-05-19
- Context window
- 1M tokens
- Input price
- $2.50 / Mtok
- Output price
- $7.50 / Mtok
Benchmark comparison
| Benchmark | MiniCPM5-1B | Qwen3.7 Max |
|---|---|---|
| AA Intelligence Index | 17.9 | 56.6 ✓ |
| GPQA Diamond | 26.9% | 92.3% ✓ |
| HLE | 4.6% | 38.1% ✓ |
| IF-Bench | 35.2% | 80.5% ✓ |
| LiveCodeBench Reasoning | 4.7% | 69.0% ✓ |
| SciCode | 1.4% | 48.8% ✓ |
| TAU2-bench | 82.5% | 94.7% ✓ |
| TerminalBench-Hard | 0.0% | 50.8% ✓ |
Pricing comparison
| Metric | MiniCPM5-1B | Qwen3.7 Max |
|---|---|---|
| Input ($/Mtok) | $0.00 | $2.50 |
| Output ($/Mtok) | $0.00 | $7.50 |
| Cached input ($/Mtok) | — | — |
| Cost per 1M-token roundtrip (1M in + 1M out) | $0.00 | $10.00 |
Context window & modalities
| Attribute | MiniCPM5-1B | Qwen3.7 Max |
|---|---|---|
| Context window | 128K tokens | 1M tokens |
| Input modalities | text | text |
| Output modalities | text | text |
| Knowledge cutoff | — | — |
Verdict by use case
Coding
Insufficient data
Basis: SWE-bench
No shared coding benchmark.
Reasoning
→ Qwen3.7 Max
Basis: GPQA Diamond
MiniCPM5-1B 26.9% vs Qwen3.7 Max 92.3% on GPQA Diamond.
Math
Insufficient data
Basis: MATH / AIME
No shared math benchmark.
Long context
→ Qwen3.7 Max
Basis: Context window
MiniCPM5-1B 128K tokens vs Qwen3.7 Max 1M tokens.
Cost
→ MiniCPM5-1B
Basis: Input $/Mtok
MiniCPM5-1B $0/Mtok vs Qwen3.7 Max $2.5/Mtok input.
Changelog & releases
MiniCPM5-1B
Released 2026-05-25
Qwen3.7 Max
Released 2026-05-19