Pairwise benchmark snapshot · Aug 17, 2026
In this head-to-head showdown, Mistral Large 3 delivers higher overall intelligence and human-preferred responses (Elo 1,456 vs 1,280), while Mistral Large 3 leads in SWE-bench software engineering benchmarks (55.4%), while Mistral Large 3 is more budget-friendly at $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
2024 workhorse. Still a high-intent compare against GPT-4o.
Mistral European flagship with strong function calling.
Δ 176 Arena Elo pts
112 tok/s
$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 | Claude 3.5 Sonnet | Mistral Large 3 | Advantage Delta |
|---|---|---|---|
| Preference Elo | +176 | ||
| LiveBench | +9.7% | ||
| SWE-bench | +6.4% | ||
| GPQA Diamond | +9.1% | ||
| Time to first token | +90 ms | ||
| Output speed | 80 tok/s | 112 tok/s | +32 tok/s |
| Input price | +$1/1M | ||
| Output price | +$9/1M | ||
| Context window | +72k |
Simulate monthly production API costs in USD (US Dollar).
Mistral Large 3 is estimated to save $170.00/month ($2,040/year).
Higher SWE-bench (55.4%).
Lower output list price ($6/1M).
Lower TTFT (190 ms).
Larger window (200k).
Both accept images. Defaulting to the higher-Elo side (Mistral Large 3).
| Target Workload | Recommended Pick | Evaluation Rationale |
|---|---|---|
| Repo / coding agents | Mistral Large 3 | Higher SWE-bench (55.4%). |
| High-volume chat | Mistral Large 3 | Lower output list price ($6/1M). |
| Voice / low-latency UI | Mistral Large 3 | Lower TTFT (190 ms). |
| Long-document RAG | Claude 3.5 Sonnet | Larger window (200k). |
| Screenshots / vision | Mistral Large 3 | Both accept images. Defaulting to the higher-Elo side (Mistral Large 3). |
No comments posted on this matchup yet. Be the first to share an evaluation note!
Dynamic OpenGraph banner generated at /compare/claude-3-5-sonnet-vs-mistral-large-3/opengraph-image
Verified Head-to-Head Telemetry
