Mistral Large 3 vs Claude Sonnet 4.6
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Mistral
|
by Anthropic
|
|---|---|---|
| Overview | ||
| Status | Current mid tier | Current mid tier |
| Released | Nov 1, 2025 | Jan 15, 2026 |
| Pricing per million tokens | ||
| Input | $0.500/Mtok | $3.00/Mtok |
| Output | $1.50/Mtok | $15.00/Mtok |
| Blended avg | $0.750/Mtok | $6.00/Mtok |
| Cached input | — | $0.300/Mtok |
| Specifications | ||
| Context window | 128K tokens | 1M tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
textimage
|
| Benchmarks sources: Mistral model card, Artificial Analysis / Vellum LLM Leaderboard | ||
| Avg benchmark score | 53.6 | 70.4 |
| Perf / dollar | 71.5 | 11.7 |
| GPQA Diamond | 58 | 89.9 |
| Humanity's Last Exam | 18 | 19.1 |
| ARC-AGI 2 | 20 | 58.3 |
| AIME 2025 | 52 | 83 |
| MMMLU | 78 | 89.3 |
| HumanEval | 85 | 79.6 |
| SWE-Bench Verified | 35 | — |
| Terminal-Bench 2.1 | — | 59.1 |
| LiveCodeBench | — | 72.4 |
| MCP Atlas | — | 69.5 |
| BrowseComp | — | 76.2 |
| OSWorld-Verified | — | 78.5 |
| BFCL | 68 | — |
| MATH 500 | 68 | — |
| AutoBench | — | 5.3 |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 15.9 | 48.4 |
| AA Agentic Index | 5.5 | 42.1 |
| AA-Omniscience Index (−100–100) | -39.6 | 12.2 |
| LMSYS Chatbot Arena | 1414.7 ELO | 1472 ELO |
| Providers | ||
| Available from |
Mistral — $0.500/$1.50/Mtok
|
Anthropic — $3.00/$15.00/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Mistral Large 3 | Claude Sonnet 4.6 | Savings |
|---|---|---|---|
| 1M tokens | $0.75 | $6 | $5.25 (87.5%) |
| 10M tokens | $7.5 | $60 | $52.5 (87.5%) |
| 100M tokens | $75 | $600 | $525 (87.5%) |
| 1000M tokens | $750 | $6000 | $5250 (87.5%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.750/Mtok blended vs $6.00 — 87.5% less on the same 50/50 token mix
- your workload re-reads context (agents, RAG, long chats): cached input costs $0.300/Mtok — 90% off its list input price, a discount Mistral Large 3 doesn't offer
- you need the longer context: 1M tokens vs 128K (7.8×)
- raw capability matters more than price: 70.4 vs 53.6 average benchmark score
The cheaper option here — Mistral Large 3 costs $0.750/Mtok blended on Mistral.
Summary
Mistral Large 3 by Mistral costs $0.500/Mtok input and $1.50/Mtok output, with a 128K-token context window. It supports text input.
Claude Sonnet 4.6 by Anthropic costs $3.00/Mtok input and $15.00/Mtok output, with a 1M-token context window. It supports text, image input.
On a blended cost basis, Mistral Large 3 is 87.5% cheaper than Claude Sonnet 4.6.
On benchmarks, Claude Sonnet 4.6 scores higher (70.4 vs 53.6) on average. In terms of value, Mistral Large 3 has better performance per dollar (71.5 vs 11.7).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.