Pairwise benchmark snapshot · Aug 1, 2026
In this head-to-head showdown, Codestral 25.01 delivers higher overall intelligence and human-preferred responses (Elo 1,320 vs 1,272), while Codestral 25.01 leads in SWE-bench software engineering benchmarks (51.8%), while GPT-4o mini is more budget-friendly at $0.6/1M per 1M output tokens. Review the complete breakdown below to determine which model best fits your performance and budget requirements.
9 direct benchmark disciplines evaluated across capability, speed, and cost
Mistral code-specialist model.
Legacy small OpenAI model. Useful as a cheap baseline.
Currently comparing Codestral 25.01 vs GPT-4o mini. Alternative family tiers available.
Δ 48 Arena Elo pts
160 tok/s
$0.6 / 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 | GPT-4o mini | Advantage Delta |
|---|---|---|---|
| Preference Elo | +48 | ||
| Coding Elo | — | — | |
| LiveBench | +5.9% | ||
| SWE-bench | +10.6% | ||
| GPQA Diamond | +1.7% | ||
| Time to first token | +20 ms | ||
| Output speed | 148 tok/s | 160 tok/s | +12 tok/s |
| Input price | $0.3/1M | $0.15/1M | +$0.15/1M |
| Output price | $0.9/1M | $0.6/1M | +$0.3/1M |
| Context window | +128k |
Simulate monthly production API costs in USD (US Dollar).
GPT-4o mini is estimated to save $9.75/month ($117/year).
Higher SWE-bench (51.8%).
Lower output list price ($0.6/1M).
Lower TTFT (130 ms).
Larger window (256k).
GPT-4o mini 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 | GPT-4o mini | Lower output list price ($0.6/1M). |
| Voice / low-latency UI | GPT-4o mini | Lower TTFT (130 ms). |
| Long-document RAG | Codestral 25.01 | Larger window (256k). |
| Screenshots / vision | GPT-4o mini | GPT-4o mini 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-gpt-4o-mini/opengraph-image
Verified Head-to-Head Telemetry