Mistral Large 4 (High) scores 26 on Intelligence Index at 161 tokens/s
ArtificialAnlys · x · 2026-10-29
Artificial Analysis published full benchmarks for Mistral Large 4 (High): 26 on the Intelligence Index (rank #8/19, above the median of 23), 161.3 output tokens/s, and 1M-token context. Pricing is $0.70/1M input and $2.10/1M output tokens with a 90% cache discount — somewhat pricey vs medians of $0.43/$1.50. The open-weights MoE model has 1.1T total and 52B active parameters, accepts text and image input, and is notably fast though somewhat verbose (110M tokens generated during evaluation).
More from Models
- AI Code Security Finally Improves: Veracode Benchmark Pass Rate Jumps From 56% to 62% — WeldPond · 2026-10-30
- Anthropic exec confirms $500 plan can nearly saturate most bug hunters' agent usage — rez0__ · 2026-10-30
- 40 days of coding-agent telemetry show a provider silently swapped model weights — Jipok_ · 2026-10-30
- Local Gemma 'completely good enough' for non-coding tasks, designer finds — michalmalewicz · 2026-10-30
- Gemini Pro silently downgraded to Flash all day citing high demand — General_Internet_511 · 2026-10-30
- Baseten releases joey-1, a 2B open-source decision model with single-forward-pass probabilities — baseten · 2026-10-30