Pairwise benchmark snapshot · Aug 1, 2026
In this head-to-head showdown, Kimi Chat 1.5 delivers higher overall intelligence and human-preferred responses (Elo 1,420 vs 1,320), while Codestral 25.01 leads in SWE-bench software engineering benchmarks (51.8%), while Kimi Chat 1.5 is more budget-friendly at $0.8/1M per 1M output tokens, while Codestral 25.01 provides faster response streaming (148 tok/s). 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 ultra-long context model supporting up to 2 million tokens per request.
Currently comparing Codestral 25.01 vs Kimi Chat 1.5. Alternative family tiers available.
Δ 100 Arena Elo pts
148 tok/s
$0.8 / 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 Chat 1.5 | Advantage Delta |
|---|---|---|---|
| Preference Elo | +100 | ||
| Coding Elo | +12 | ||
| LiveBench | +4% | ||
| SWE-bench | +0.8% | ||
| GPQA Diamond | +13.1% | ||
| Time to first token | +60 ms | ||
| Output speed | 148 tok/s | 95 tok/s | +53 tok/s |
| Input price | $0.3/1M | $0.2/1M | +$0.1/1M |
| Output price | $0.9/1M | $0.8/1M | +$0.1/1M |
| Context window | +1.7M |
Simulate monthly production API costs in USD (US Dollar).
Kimi Chat 1.5 is estimated to save $5.00/month ($60/year).
Higher SWE-bench (51.8%).
Lower output list price ($0.8/1M).
Lower TTFT (150 ms).
Larger window (2M).
Kimi Chat 1.5 is the side marked multimodal in the catalog.
| Target Workload | Recommended Pick | Evaluation Rationale |
|---|---|---|
| Repo / coding agents | Codestral 25.01 | Higher SWE-bench (51.8%). |
| High-volume chat | Kimi Chat 1.5 | Lower output list price ($0.8/1M). |
| Voice / low-latency UI | Codestral 25.01 | Lower TTFT (150 ms). |
| Long-document RAG | Kimi Chat 1.5 | Larger window (2M). |
| Screenshots / vision | Kimi Chat 1.5 | Kimi Chat 1.5 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-1-5-long/opengraph-image
Verified Head-to-Head Telemetry