Benchmark scores
Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.
LLM Comparison
MiniMax-M3 vs Hy4 Preview: benchmark scores, pricing & comparison.
Side-by-side MiniMax-M3 vs Hy4 Preview comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.
Rank #28 vs #29AskClash overall scores 38.1 vs 36.1.
Pricing $0.30/$1.20 vs $0.83/$2.50Input and output token prices per 1M tokens when published.
Open Weight vs Open WeightMiniMax vs Tencent.
MiniMax-M3 vs Hy4 Preview benchmark comparison
Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.
| Metric | MiniMax-M3 | Hy4 Preview |
|---|---|---|
| Overall Score | 38.1 | 36.1 |
| Leaderboard Rank | #28 | #29 |
| ACB | 29.8 | — |
| RWT | 8.5 | 8.5 |
| HLE | 37.1 | 43.4 |
| GPQA | 92.9 | 92.3 |
| IFEval | 82.9 | — |
| SWE-bench | 80.5 | — |
| SWE-Pro | 59.0 | 65.7 |
| Terminal-Bench | 66.0 | 85.4 |
| DeepSWE | — | 64.3 |
| GDPval-AA | 58.4 | 1678.0 |
| OSWorld | 70.1 | — |
| MCP Atlas | 74.2 | 83.7 |
| Finance Agent | 48.3 | — |
| MMMU-Pro | 78.1 | — |
| Tau2 | 88.9 | — |
| Input Price (per 1M tokens) | $0.30 | $0.83 |
| Output Price (per 1M tokens) | $1.20 | $2.50 |
| Context Window | 1M | 1M |
| Benchmarks Published | 14 | 7 |
MiniMax-M3 vs Hy4 Preview head-to-head charts
MiniMax-M3 leads 2 and Hy4 Preview leads 5 of 8 shared benchmarks. MiniMax-M3 is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.
MiniMax-M3Hy4 Preview
Overall
RWT
HLE
GPQA
SWE-Pro
Terminal-Bench
GDPval-AA
MCP Atlas
MiniMax-M3
Input$0.30
Output$1.20
Workload$0.54
Context1M
Hy4 Preview
Input$0.83
Output$2.50
Workload$1.33
Context1M
Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.
More MiniMax-M3 and Hy4 Preview comparisons
Explore how MiniMax-M3 and Hy4 Preview stack up against other top-ranked LLMs.
How to read this comparison
Token pricing
Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.
Coverage matters
Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.
This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.