Skip to content
aiqbench

Mistral · model passport

Mistral Small 2506

mistral-small-2506
  • Open weights
  • Apache 2.0 licence
  • Released 2025-06-01(from model name)
6/27axes covered
Overall · LMArena
1,356#194 of 396
Best percentile
54.9BFCL v4 (function calling)
Cohort standing
48.6median 50.6

What the data says

Benchmarked on 6 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 26.9 percentile points between its best and worst axis — 54.9 pct on BFCL v4 (function calling) versus 28 pct on Vision Arena.

  • BFCL v4 (function calling)Dormant board54.9 pct37.1%Verify →
  • Coding52.9 pct1,411Verify →
  • Overall51.3 pct1,356Verify →
  • Hard prompts51.3 pct1,373Verify →
  • Instruction following49.2 pct1,337Verify →
  • Vision Arena28 pct1,140Verify →
  • WebDev ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • IFBench (Artificial Analysis)Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

  • mistral-small-2506 stands at 48.6 (raw mean 47.9) — measured on 6 of 27 axes.

    standingtemplateVerify →

  • mistral-small-2506 stands at 48.6 versus a cohort median of 50.6 across 145 models released within 180 days — below the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →