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 GPT-6 Luna: benchmark scores, pricing & comparison.
Side-by-side MiniMax-M3 vs GPT-6 Luna 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 #53 vs #56AskClash overall scores 45.6 vs 43.8.
Pricing $0.30/$1.20 vs $0.10/$0.50Input and output token prices per 1M tokens when published.
Open Weight vs ProprietaryMiniMax vs OpenAI.
MiniMax-M3 vs GPT-6 Luna benchmark comparison
Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.
| Metric | MiniMax-M3 | GPT-6 Luna |
|---|---|---|
| Overall Score | 45.6 | 43.8 |
| Leaderboard Rank | #53 | #56 |
| ACB | 29.8 | 50.2 |
| RWT | 8.5 | — |
| Coding Agent Index | — | 41.1 |
| HLE | 37.1 | 38.5 |
| GPQA | 92.9 | — |
| IFEval | 82.9 | — |
| SWE-bench | 80.5 | — |
| SWE-Pro | 59.0 | — |
| SWE-Atlas | — | 44.4 |
| Terminal-Bench | 66.0 | — |
| DeepSWE | — | 66.6 |
| GDPval-AA | 58.4 | 1367.1 |
| OSWorld | 70.1 | — |
| MCP Atlas | 74.2 | — |
| Finance Agent | 48.3 | — |
| MMMU-Pro | 78.1 | 75.5 |
| ARC-AGI 2 | — | 59.3 |
| Tau2 | 88.9 | — |
| Input Price (per 1M tokens) | $0.30 | $0.10 |
| Output Price (per 1M tokens) | $1.20 | $0.50 |
| Context Window | 1M | 1.05M |
| Benchmarks Published | 14 | 9 |
MiniMax-M3 vs GPT-6 Luna head-to-head charts
MiniMax-M3 leads 2 and GPT-6 Luna leads 3 of 5 shared benchmarks. GPT-6 Luna is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.
MiniMax-M3GPT-6 Luna
Overall
ACB
HLE
GDPval-AA
MMMU-Pro
MiniMax-M3
Input$0.30
Output$1.20
Workload$0.54
Context1M
GPT-6 Luna
Input$0.10
Output$0.50
Workload$0.20
Context1.05M
Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.
More MiniMax-M3 and GPT-6 Luna comparisons
Explore how MiniMax-M3 and GPT-6 Luna 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.