Noometry

Model comparison

Claude Opus 4.1 vs Step 3.7 Flash

Claude Opus 4.1 is the stronger model overall, scoring 40.8 to 36.5 on the Noometry Index. Step 3.7 Flash costs 72× less per token, which makes it the better buy when Claude Opus 4.1's lead doesn't matter for your workload.

Last verified . 1 shared benchmarks.

Claude Opus 4.1 Anthropic

40.8

Rank #136 Confirmed

Step 3.7 Flash StepFun

36.5

Rank #207 Reported

Summary

  • They share 1 benchmark with published results for both. Claude Opus 4.1 scores higher in 2 categories and Step 3.7 Flash in 1 category; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where Step 3.7 Flash leads 40.9 to 22.0.
  • Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
  • Step 3.7 Flash accepts more context: 256K tokens versus 200K.
  • Step 3.7 Flash has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.1Step 3.7 Flash
ProviderAnthropicStepFun
Noometry Index40.836.5
Released2025-08-052026-05-29
WeightsProprietaryOpen
Context window200K256K
Max output32K256K
Input $ / M tokens$15$0.18
Output $ / M tokens$75$1.11
Results tracked485

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

Category by category

Coding Claude Opus 4.1 leads

Claude Opus 4.1: 44.3 (#69), Step 3.7 Flash: 39.4 (#147)

BenchmarkClaude Opus 4.1Step 3.7 Flash
ALE-Bench674.77694.12
SWE-bench Verified73.3%—
LMArena WebDev1390—
SciCode—40%
WeirdML45.9%—
LMArena Coding1479—
AlgoTune1.34—

Agentic & Tool Use Not comparable

Claude Opus 4.1: 34.8 (#38), Step 3.7 Flash: —

BenchmarkClaude Opus 4.1Step 3.7 Flash
Terminal-Bench38%—
GDPval43.6%—
Cybench42%—
DeepResearch Bench48.3%—
LMArena Search1148—
METR Time Horizons66.8%—

Reasoning Claude Opus 4.1 leads

Claude Opus 4.1: 31.6 (#70), Step 3.7 Flash: 20.9 (#211)

BenchmarkClaude Opus 4.1Step 3.7 Flash
SimpleBench60%—
NYT Connections (extended)—39.7%
CritPt—2.3%
Chess Puzzles7%—
EnigmaEval7.2%—
EBR-Bench7.9%—
LMArena Hard Prompts1443—
Mystery Game Puzzles21%—
DTBench80%—
LMCA37.1%—
Epoch Capabilities Index144.11—
ForecastBench62—

Math Step 3.7 Flash leads

Claude Opus 4.1: 22.0 (#267), Step 3.7 Flash: 40.9 (#74)

BenchmarkClaude Opus 4.1Step 3.7 Flash
FrontierMath (Tiers 1-3)12.6%—
FrontierMath Tier 42.4%—
MathArena Final-Answer Competitions—68.5%
OTIS Mock AIME 2024-202568.9%—
LMArena Math1430—
FrontierMath (Feb 2025 set)7.2%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Not comparable

Claude Opus 4.1: 41.9 (#93), Step 3.7 Flash: —

BenchmarkClaude Opus 4.1Step 3.7 Flash
GPQA Diamond77.3%—
Humanity's Last Exam11.5%—
Confabulations17.1%—
Vectara Hallucination Rate11.8%—
LMArena Expert1439—

Multimodal Not comparable

Claude Opus 4.1: 26.2 (#114), Step 3.7 Flash: —

BenchmarkClaude Opus 4.1Step 3.7 Flash
VPCT35%—

Multilingual Not comparable

Claude Opus 4.1: 52.1 (#90), Step 3.7 Flash: —

BenchmarkClaude Opus 4.1Step 3.7 Flash
LMArena Non-English1405—
LMArena Chinese1427—
LMArena French1432—
LMArena German1412—
LMArena Japanese1378—
LMArena Korean1381—
LMArena Russian1421—
LMArena Spanish1448—

Instruction Following Not comparable

Claude Opus 4.1: 75.8 (#53), Step 3.7 Flash: —

BenchmarkClaude Opus 4.1Step 3.7 Flash
LMArena Instruction Following1436—

Long Context Not comparable

Claude Opus 4.1: 44.5 (#60), Step 3.7 Flash: —

BenchmarkClaude Opus 4.1Step 3.7 Flash
LMArena Longer Query1455—

Writing & Preference Not comparable

Claude Opus 4.1: 62.6 (#70), Step 3.7 Flash: —

BenchmarkClaude Opus 4.1Step 3.7 Flash
LMArena Text1419—
LMArena Creative Writing1412—
Short-Story Creative Writing84.7%—
LMArena Multi-Turn1444—

Frequently asked questions

Is Claude Opus 4.1 better than Step 3.7 Flash?

Claude Opus 4.1 is the stronger model overall, scoring 40.8 to 36.5 on the Noometry Index. Step 3.7 Flash costs 72× less per token, which makes it the better buy when Claude Opus 4.1's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.1 or Step 3.7 Flash?

Step 3.7 Flash is cheaper. It lists at $0.18 per million input tokens and $1.11 per million output tokens; Claude Opus 4.1 lists at $15 and $75.

Is Claude Opus 4.1 or Step 3.7 Flash better for coding?

Claude Opus 4.1 scores higher on coding benchmarks: 44.3 versus 39.4 in the Noometry coding category.

Which has the bigger context window?

Step 3.7 Flash does, with 256K tokens against 200K.

How many benchmarks do Claude Opus 4.1 and Step 3.7 Flash share?

1 benchmark has published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Step 3.7 Flash has 5.

Related comparisons

Go deeper