SI Index Data as of Oct 9, 2026

Mistral Medium 3: Price, Context, Benchmarks, and Release Details

mistral provisional listing · first seen Oct 8, 2026 · score computed Oct 9, 2026, 01:09 UTC
33.0
SI Score (method si-v3-retained-evidence-2)
#134 of 140 ranked
85% confidence 85 percent, High confidence — 4 of 7 expected sources in
Coverage 68% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 3.8
Math (weight 15 percent) 65.2
Preference (weight 15 percent) 45.6
Reasoning (weight 30 percent) 22.9

Pillar weights: reasoning 30% · math 15% · coding 40% · preference 15%. Benchmark results use fixed 0–100 scales before averaging; incomplete evidence is shrunk toward 50.

Facts

Input price / 1M
not yet reported
Output price / 1M
not yet reported
Context window
131Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
131Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
May 7, 2025models.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Open weights
Nomodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
License
not yet reported
Input modalities
text, imagemodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

Benchmark results

6 results
Benchmark Raw result Normalized (0–100) Pillar
gpqa diamond 59.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published May 7, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		59.5 reasoning
hle scale 4.5%Humanity’s Last ExamPotential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. [variant] Published May 13, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		4.5 reasoning
lmarena text 1165.1 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 		45.6 preference
math level 5 81.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published May 7, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		81.6 math
otis mock aime 2024 2025 32.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published May 7, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		32.2 math
terminal bench 3.8%Official model cards via models.devLab-reported; metric success rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] Published May 30, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		3.8 coding

Normalization uses fixed absolute 0–100 scales for each unit, independently of other models that have a result on each benchmark. Coverage and evidence breadth still affect the composite; compare the evaluation conditions before reading a small score gap as decisive. “lab-reported” marks the provider's own published figure.

Sources: in and pending

in Reported (4)

  • Epoch AI Benchmarking · arrived Oct 8, 2026
  • Humanity’s Last Exam · arrived Oct 8, 2026
  • Official model cards via models.dev · arrived Oct 8, 2026
  • LMArena / Arena · arrived Oct 8, 2026

pending Awaiting (3)

  • ARC Prize · carries 13% of expected weight
  • LiveBench · carries 13% of expected weight
  • Terminal-Bench · carries 6% of expected weight

The confidence % rises as pending sources publish. Some sources never cover some models — that is why 100% confidence arrives at 80% of expected weight, not at full coverage.