Noometry

Model comparison

Claude Fable 5.1 vs Pixtral 12B

Claude Fable 5.1 has enough public results to be ranked (#2); Pixtral 12B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Claude Fable 5.1 Anthropic

69.0

Rank #2 Confirmed

Pixtral 12B Mistral AI

31.3

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. Claude Fable 5.1 scores higher in 1 category and Pixtral 12B in 0 categories; one gap is clear of the uncertainty.
  • The widest gap is in multimodal, where Claude Fable 5.1 leads 53.9 to 23.9.
  • Pixtral 12B is cheaper at $0.15 / $0.15 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
  • Claude Fable 5.1 accepts more context: 1M tokens versus 128K.
  • Pixtral 12B has downloadable open weights; the other is API-only.

Side by side

Claude Fable 5.1Pixtral 12B
ProviderAnthropicMistral AI
Noometry Index69.031.3
Released2026-09-012024-09-01
WeightsProprietaryOpen
Context window1M128K
Max output128K128K
Input $ / M tokens$10$0.15
Output $ / M tokens$50$0.15
Results tracked522

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Claude Fable 5.1: 74.7 (#1), Pixtral 12B: —

BenchmarkClaude Fable 5.1Pixtral 12B
FrontierCode50.9%—
CursorBench51.8%—
LMArena WebDev1744—
FrontierSWE56.3%—
SciCode63.1%—
GSO88.2%—
WeirdML92.9%—
LMArena Coding1528—
MirrorCode73.3%—
ALE-Bench2,143—

Agentic & Tool Use Not comparable

Claude Fable 5.1: 50.7 (#5), Pixtral 12B: —

BenchmarkClaude Fable 5.1Pixtral 12B
APEX-Agents68.6%—
Remote Labor Index17.9%—
GDP.pdf29.6%—
Vending-Bench 25,422—

Reasoning Not comparable

Claude Fable 5.1: 76.7 (#7), Pixtral 12B: —

BenchmarkClaude Fable 5.1Pixtral 12B
ARC-AGI-290%—
NYT Connections (extended)90%—
ARC-AGI-197.5%—
CritPt31.1%—
Chess Puzzles47%—
EBR-Bench57.1%—
LMArena Hard Prompts1526—
Mystery Game Puzzles58%—
DTBench97.6%—
LMCA65.5%—
Epoch Capabilities Index164.7—

Math Not comparable

Claude Fable 5.1: 89.6 (#4), Pixtral 12B: —

BenchmarkClaude Fable 5.1Pixtral 12B
FrontierMath (Tiers 1-3)90.2%—
FrontierMath Tier 487.8%—
OTIS Mock AIME 2024-2025100%—
ProofBench100%—
LMArena Math1525—
FrontierMath Erdős0%—

Knowledge Not comparable

Claude Fable 5.1: 69.6 (#6), Pixtral 12B: —

BenchmarkClaude Fable 5.1Pixtral 12B
Humanity's Last Exam46.5%—
SimpleQA Verified70.8%—
LMArena Expert1535—

Multimodal Claude Fable 5.1 leads

Claude Fable 5.1: 53.9 (#4), Pixtral 12B: 23.9 (#127)

BenchmarkClaude Fable 5.1Pixtral 12B
LMArena Vision13181009
GeoBench—37%
Blueprint-Bench 241.9%—
Furniture Assembly70%—
LMArena Document1513—

Multilingual Not comparable

Claude Fable 5.1: 59.1 (#3), Pixtral 12B: —

BenchmarkClaude Fable 5.1Pixtral 12B
LMArena Non-English1507—
LMArena Chinese1586—
LMArena French1525—
LMArena German1500—
LMArena Japanese1543—
LMArena Korean1534—
LMArena Russian1521—
LMArena Spanish1516—

Instruction Following Not comparable

Claude Fable 5.1: 79.2 (#6), Pixtral 12B: —

BenchmarkClaude Fable 5.1Pixtral 12B
LMArena Instruction Following1517—

Long Context Not comparable

Claude Fable 5.1: 46.7 (#20), Pixtral 12B: —

BenchmarkClaude Fable 5.1Pixtral 12B
LMArena Longer Query1522—

Writing & Preference Not comparable

Claude Fable 5.1: 79.2 (#2), Pixtral 12B: —

BenchmarkClaude Fable 5.1Pixtral 12B
LMArena Text1510—
LMArena Creative Writing1507—
EQ-Bench Creative Writing2162—
LMArena Multi-Turn1492—

Frequently asked questions

Is Claude Fable 5.1 better than Pixtral 12B?

Claude Fable 5.1 has enough public results to be ranked (#2); Pixtral 12B does not yet, so treat this comparison as directional.

Which is cheaper, Claude Fable 5.1 or Pixtral 12B?

Pixtral 12B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Claude Fable 5.1 lists at $10 and $50.

Which has the bigger context window?

Claude Fable 5.1 does, with 1M tokens against 128K.

How many benchmarks do Claude Fable 5.1 and Pixtral 12B share?

1 benchmark has published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Pixtral 12B has 2.

Related comparisons

Go deeper