Noometry

Model comparison

Claude Sonnet 4.5 vs Devstral Small 2505

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 34.3 on the Noometry Index. Devstral Small 2505 costs 40× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Last verified . 4 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

Devstral Small 2505 Mistral AI

34.3

Rank #233 Reported

Summary

  • They share 4 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 2 categories and Devstral Small 2505 in 0 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Claude Sonnet 4.5 leads 47.3 to 38.9.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 57.9% for Claude Sonnet 4.5 and 37.7% for Devstral Small 2505.
  • Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • Claude Sonnet 4.5 accepts more context: 200K tokens versus 128K.
  • Devstral Small 2505 has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.5Devstral Small 2505
ProviderAnthropicMistral AI
Noometry Index44.134.3
Released2025-09-292025-05-07
WeightsProprietaryOpen
Context window200K128K
Max output64K128K
Input $ / M tokens$3$0.10
Output $ / M tokens$15$0.30
Results tracked734

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

Category by category

Coding Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 47.3 (#61), Devstral Small 2505: 38.9 (#166)

BenchmarkClaude Sonnet 4.5Devstral Small 2505
SWE-bench Verified (bash only)71.4%56.4%
SciCode44.7%28.8%
SWE-bench Verified71.3%—
LMArena WebDev1393—
SWE-bench Multilingual67%—
GSO14.7%—
WeirdML47.7%—
LMArena Coding1489—
ALE-Bench796.15—
AlgoTune1.52—

Agentic & Tool Use Not comparable

Claude Sonnet 4.5: 38.3 (#32), Devstral Small 2505: —

BenchmarkClaude Sonnet 4.5Devstral Small 2505
Terminal-Bench46.5%—
Berkeley Function Calling Leaderboard73.2%—
GDPval42.5%—
Remote Labor Index2.1%—
τ²-bench Airline72%—
τ²-bench Banking25.3%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
LMArena Search1159—
METR Time Horizons67.4%—
Vending-Bench 23,839—

Reasoning Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 26.9 (#125), Devstral Small 2505: 19.7 (#252)

BenchmarkClaude Sonnet 4.5Devstral Small 2505
Kagi LLM Benchmark57.9%37.7%
CritPt1.1%0%
ARC-AGI-213.6%—
SimpleBench54.3%—
NYT Connections (extended)37.3%—
ARC-AGI-163.7%—
Chess Puzzles12%—
EnigmaEval6%—
EBR-Bench2.4%—
LMArena Hard Prompts1462—
Mystery Game Puzzles17%—
DTBench83.2%—
LMCA38.8%—
Epoch Capabilities Index146.84—
ForecastBench61.9—

Math Not comparable

Claude Sonnet 4.5: 32.3 (#216), Devstral Small 2505: —

BenchmarkClaude Sonnet 4.5Devstral Small 2505
FrontierMath (Tiers 1-3)23.9%—
FrontierMath Tier 42.4%—
OTIS Mock AIME 2024-202577.8%—
ProofBench19%—
Omni-MATH55.3%—
LMArena Math1449—
MATH Level 597.7%—
FrontierMath (Feb 2025 set)15.2%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Not comparable

Claude Sonnet 4.5: 48.4 (#76), Devstral Small 2505: —

BenchmarkClaude Sonnet 4.5Devstral Small 2505
GPQA Diamond82.3%—
Humanity's Last Exam13.7%—
SimpleQA Verified30.7%—
MMLU-Pro86.9%—
Vectara Hallucination Rate12%—
GPQA (HELM)68.6%—
LMArena Expert1482—

Multimodal Not comparable

Claude Sonnet 4.5: 34.8 (#89), Devstral Small 2505: —

BenchmarkClaude Sonnet 4.5Devstral Small 2505
VPCT39.8%—
LMArena Document1450—

Multilingual Not comparable

Claude Sonnet 4.5: 53.4 (#69), Devstral Small 2505: —

BenchmarkClaude Sonnet 4.5Devstral Small 2505
LMArena Non-English1425—
LMArena Chinese1459—
LMArena French1458—
LMArena German1427—
LMArena Japanese1390—
LMArena Korean1403—
LMArena Russian1437—
LMArena Spanish1457—

Instruction Following Not comparable

Claude Sonnet 4.5: 75.0 (#78), Devstral Small 2505: —

BenchmarkClaude Sonnet 4.5Devstral Small 2505
IFEval85%—
LMArena Instruction Following1459—

Long Context Not comparable

Claude Sonnet 4.5: 45.2 (#46), Devstral Small 2505: —

BenchmarkClaude Sonnet 4.5Devstral Small 2505
LMArena Longer Query1476—

Writing & Preference Not comparable

Claude Sonnet 4.5: 66.5 (#34), Devstral Small 2505: —

BenchmarkClaude Sonnet 4.5Devstral Small 2505
LMArena Text1439—
LMArena Creative Writing1442—
EQ-Bench Creative Writing1678—
WildBench85.4%—
LMArena Multi-Turn1465—

Frequently asked questions

Is Claude Sonnet 4.5 better than Devstral Small 2505?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 34.3 on the Noometry Index. Devstral Small 2505 costs 40× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.5 or Devstral Small 2505?

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Devstral Small 2505 better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 38.9 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.5 does, with 200K tokens against 128K.

How many benchmarks do Claude Sonnet 4.5 and Devstral Small 2505 share?

4 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Devstral Small 2505 has 4.

Related comparisons

Go deeper