Pairwise benchmark snapshot · Aug 17, 2026
In this head-to-head showdown, MiniMax M2.5 delivers higher overall intelligence and human-preferred responses (Elo 1,478 vs 1,310), while MiniMax M2.5 leads in SWE-bench software engineering benchmarks (75.8%), while MiniMax M2.5 is more budget-friendly at $0.9/1M per 1M output tokens. Review the complete breakdown below to determine which model best fits your performance and budget requirements.
MiniMax coding model. Tied near the top of official SWE-bench bash-only in Feb 2026.
Δ 168 Arena Elo pts
90 tok/s
$0.8999999999999999 / 1M output
Relative percentile scores computed across all active models in the benchmark catalog.
Each spoke is a skill. Farther from the center is better (0–100th percentile). Tap any dot to inspect details.
Category wins across reasoning intelligence, generation speed, and token cost.
Preference Elo, Coding proficiency, SWE-bench & LiveBench accuracy
Generation throughput and time to first token responsiveness
Cost per million tokens and max context window length
| Benchmark | DeepSeek V3 | MiniMax M2.5 | Advantage Delta |
|---|---|---|---|
| Preference Elo | MiniMax M2.5 (+168) | ||
| Coding Elo | — | — | |
| LiveBench | MiniMax M2.5 (+9%) | ||
| SWE-bench | MiniMax M2.5 (+27.2%) | ||
| GPQA Diamond | MiniMax M2.5 (+17.1%) | ||
| Time to first token | MiniMax M2.5 (+130 ms) | ||
| Output speed | 66 tok/s | 90 tok/s | MiniMax M2.5 (+24 tok/s) |
| Input price | $0.2574/1M | $0.22/1M | MiniMax M2.5 (+$0.0374/1M) |
| Output price | $1.03/1M | $0.9/1M | MiniMax M2.5 (+$0.1287/1M) |
| Context window | MiniMax M2.5 (+41k) |
Simulate monthly production API costs in USD (US Dollar).
MiniMax M2.5 is estimated to save $3.24/month ($39/year).
Higher SWE-bench (75.8%).
Lower output list price ($0.9/1M).
Lower TTFT (250 ms).
Larger window (205k).
MiniMax M2.5 is the side marked multimodal in the catalog.
| Target Workload | Recommended Pick | Evaluation Rationale |
|---|---|---|
| Repo / coding agents | MiniMax M2.5 | Higher SWE-bench (75.8%). |
| High-volume chat | MiniMax M2.5 | Lower output list price ($0.9/1M). |
| Voice / low-latency UI | MiniMax M2.5 | Lower TTFT (250 ms). |
| Long-document RAG | MiniMax M2.5 | Larger window (205k). |
| Screenshots / vision | MiniMax M2.5 | MiniMax M2.5 is the side marked multimodal in the catalog. |
No comments posted on this matchup yet. Be the first to share an evaluation note!
The real PNG is generated at /compare/deepseek-v3-vs-minimax-m2-5/opengraph-image for crawlers.
Verified head-to-head card
