Pairwise benchmark snapshot · Aug 1, 2026
In this head-to-head showdown, Kimi K2 delivers higher overall intelligence and human-preferred responses (Elo 1,465 vs 1,320), while Kimi K2 leads in SWE-bench software engineering benchmarks (65.8%), while Codestral 25.01 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.
10 direct benchmark disciplines evaluated across capability, speed, and cost
Mistral code-specialist model.
Moonshot foundation model with strong native bilingual reasoning and 65.8% SWE-bench Verified coding baseline.
Currently comparing Codestral 25.01 vs Kimi K2. Alternative family tiers available.
Δ 145 Arena Elo pts
148 tok/s
$0.9 / 1M output
Relative percentile scores computed across all active models in the benchmark catalog.
Comparing top Western standard models with China's leading frontier rival across 6 skill dimensions. Tap any spoke or dot to inspect.
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 | Codestral 25.01 | Kimi K2 | Advantage Delta |
|---|---|---|---|
| Preference Elo | +145 | ||
| Coding Elo | +68 | ||
| LiveBench | +8.8% | ||
| SWE-bench | +14% | ||
| GPQA Diamond | +18.1% | ||
| Time to first token | +90 ms | ||
| Output speed | 148 tok/s | 85 tok/s | +63 tok/s |
| Input price | $0.3/1M | $0.35/1M | +$0.05/1M |
| Output price | $0.9/1M | $1.4/1M | +$0.5/1M |
| Context window | +128k |
Simulate monthly production API costs in USD (US Dollar).
Codestral 25.01 is estimated to save $9.25/month ($111/year).
Higher SWE-bench (65.8%).
Lower output list price ($0.9/1M).
Lower TTFT (150 ms).
Larger window (256k).
Kimi K2 is the side marked multimodal in the catalog.
| Target Workload | Recommended Pick | Evaluation Rationale |
|---|---|---|
| Repo / coding agents | Kimi K2 | Higher SWE-bench (65.8%). |
| High-volume chat | Codestral 25.01 | Lower output list price ($0.9/1M). |
| Voice / low-latency UI | Codestral 25.01 | Lower TTFT (150 ms). |
| Long-document RAG | Codestral 25.01 | Larger window (256k). |
| Screenshots / vision | Kimi K2 | Kimi K2 is the side marked multimodal in the catalog. |
No comments posted on this matchup yet. Be the first to share an evaluation note!
Dynamic OpenGraph banner generated at /compare/codestral-25-vs-kimi-k2/opengraph-image
Verified Head-to-Head Telemetry