Compare

Claude Sonnet 4.6 vs Mistral X-Large

Anthropic vs Mistral. Specs, benchmarks, and real per-task cost — all in one page.

Verdict

Claude Sonnet 4.6 leads on LMSYS ELO (1368 vs 1318). Mistral X-Large is ~2.0× cheaper on a 3:1 input:output blend. Mistral X-Large is open-weights, the other is proprietary.

Anthropic

Claude Sonnet 4.6

The workhorse. Near-Opus quality at 1/5 the cost. The default choice for production code and agent workloads.

Excellent cost/quality ratioFast inferenceGreat for Cursor/Claude Code

Mistral

Mistral X-Large

European frontier model. EU-hosted inference, strong European language coverage, Apache-licensed weights.

EU data residencyMultilingual strengthOpen license

Pricing

Input / 1M$3.00$2.00

Output / 1M$15.00$6.00

Context500K256K

Max output64K16K

LicenseProprietaryOpen weights

Released2025-11-042026-01-28

Benchmarks

LMSYS ELO1368.01318.0

MMLU Pro88.783.5

HumanEval92.188.0

SWE-Bench64.5—

MATH85.078.2

GPQA59.4—

MMMU74.1—

IFEval90.586.5

Per-task cost

Summarize a 1-hour meeting transcript$0.052$0.033

Review a 500-line pull request$0.054$0.028

Answer a customer support ticket$0.021$0.011

Extract structured data from a resume$0.030$0.016

Debug a stack trace with context$0.048$0.024

Per-call cost using published token counts for each task. Real-world prompts vary.

Tool

Interactive compare →

Add up to four models, tweak tasks live.