Compare
Mistral X-Large vs Gemini 2.5 Ultra
Mistral vs Google DeepMind. Specs, benchmarks, and real per-task cost — all in one page.
Verdict
Gemini 2.5 Ultra leads on LMSYS ELO (1385 vs 1318). Mistral X-Large is ~3.5× cheaper on a 3:1 input:output blend. Mistral X-Large is open-weights, the other is proprietary.
Mistral
Mistral X-LargeEuropean frontier model. EU-hosted inference, strong European language coverage, Apache-licensed weights.
EU data residencyMultilingual strengthOpen license
Google DeepMind
Gemini 2.5 Ultra2M-token context, native video understanding, and Google’s deepest multimodal stack. The long-context king.
2M context windowNative videoBest multimodal reasoning
Pricing
Input / 1M$2.00$7.00
Output / 1M$6.00$21.00
Context256K2.0M
Max output16K64K
LicenseOpen weightsProprietary
Released2026-01-282026-02-05
Benchmarks
LMSYS ELO1318.01385.0
MMLU Pro83.590.4
HumanEval88.090.2
SWE-Bench—58.3
MATH78.292.0
MMMU—82.1
IFEval86.589.7
Per-task cost
Summarize a 1-hour meeting transcript$0.033$0.115
Review a 500-line pull request$0.028$0.098
Answer a customer support ticket$0.011$0.038
Extract structured data from a resume$0.016$0.056
Debug a stack trace with context$0.024$0.084
Per-call cost using published token counts for each task. Real-world prompts vary.