Model comparison

DeepSeek-R1 vs Step 3.7 Flash

DeepSeek-R1 is the stronger model overall, scoring 42.3 to 37.3 on the Noometry Index. Step 3.7 Flash costs 2.2× less per token, which makes it the better buy when DeepSeek-R1's lead doesn't matter for your workload.

Last verified October 10, 2026. 3 shared benchmarks.

DeepSeek-R1

DeepSeek

42.3

Rank #115 Confirmed

Step 3.7 Flash

StepFun

37.3

Rank #207 Reported

Summary

They share 3 benchmarks with published results for both. DeepSeek-R1 scores higher in 2 categories and Step 3.7 Flash in 1 category; 2 gaps are clear of the uncertainty.
The widest gap is in coding, where DeepSeek-R1 leads 46.3 to 40.0.
Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
Step 3.7 Flash accepts more context: 256K tokens versus 164K.
Step 3.7 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek-R1 and Step 3.7 Flash specifications
	DeepSeek-R1	Step 3.7 Flash
Provider	DeepSeek	StepFun
Noometry Index	42.3	37.3
Released	2025-01-20	2026-05-29
Weights	Proprietary	Open
Context window	164K	256K
Max output	64K	256K
Input $ / M tokens	$0.50	$0.18
Output $ / M tokens	$2.15	$1.11
Results tracked	52	5

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

Category by category

Coding DeepSeek-R1 leads

DeepSeek-R1: 46.3 (#68), Step 3.7 Flash: 40.0 (#150)

Coding benchmarks
Benchmark	DeepSeek-R1	Step 3.7 Flash
SciCode	35.7%	40%
ALE-Bench	804.12	694.12
Aider Polyglot	71.4%	—
WeirdML	41.6%	—
LiveBench Coding	66.7%	—
LMArena Coding	1427	—
AlgoTune	1.7	—

Agentic & Tool Use Not comparable

DeepSeek-R1: 30.7 (#75), Step 3.7 Flash: —

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-R1	Step 3.7 Flash
DeepResearch Bench	35.1%	—
BALROG	34.9%	—
METR Time Horizons	53.8%	—

Reasoning Step 3.7 Flash leads

DeepSeek-R1: 18.6 (#278), Step 3.7 Flash: 21.6 (#219)

Reasoning benchmarks
Benchmark	DeepSeek-R1	Step 3.7 Flash
CritPt	1.1%	2.3%
ARC-AGI-2	1.3%	—
SimpleBench	40.8%	—
Kagi LLM Benchmark	69.4%	—
NYT Connections (extended)	—	39.7%
ARC-AGI-1	21.2%	—
LiveBench Reasoning	83.2%	—
LMArena Hard Prompts	1416	—
LiveBench Data Analysis	69.8%	—
Epoch Capabilities Index	141.29	—
ForecastBench	60	—
LiveBench	71.6%	—

Math Too close to call

DeepSeek-R1: 43.8 (#79), Step 3.7 Flash: 42.9 (#82)

Math benchmarks
Benchmark	DeepSeek-R1	Step 3.7 Flash
MathArena Final-Answer Competitions	—	68.5%
OTIS Mock AIME 2024-2025	66.4%	—
Omni-MATH	42.4%	—
LiveBench Math	80.7%	—
LMArena Math	1400	—
MATH Level 5	96.6%	—

Knowledge Not comparable

DeepSeek-R1: 44.5 (#87), Step 3.7 Flash: —

Knowledge benchmarks
Benchmark	DeepSeek-R1	Step 3.7 Flash
GPQA Diamond	76.3%	—
MMLU-Pro	79.3%	—
Confabulations	12.7%	—
Vectara Hallucination Rate	11.3%	—
GPQA (HELM)	66.6%	—
LMArena Expert	1394	—

Multilingual Not comparable

DeepSeek-R1: 52.4 (#85), Step 3.7 Flash: —

Multilingual benchmarks
Benchmark	DeepSeek-R1	Step 3.7 Flash
LMArena Non-English	1412	—
LMArena Chinese	1442	—
LMArena French	1417	—
LMArena German	1404	—
LMArena Japanese	1391	—
LMArena Korean	1360	—
LMArena Russian	1423	—
LMArena Spanish	1411	—

Instruction Following Not comparable

DeepSeek-R1: 72.0 (#143), Step 3.7 Flash: —

Instruction Following benchmarks
Benchmark	DeepSeek-R1	Step 3.7 Flash
LiveBench Instruction Following	80.5%	—
IFEval	78.4%	—
LMArena Instruction Following	1382	—

Long Context Not comparable

DeepSeek-R1: 45.4 (#36), Step 3.7 Flash: —

Long Context benchmarks
Benchmark	DeepSeek-R1	Step 3.7 Flash
Fiction.LiveBench	75%	—
LMArena Longer Query	1391	—

Writing & Preference Not comparable

DeepSeek-R1: 61.4 (#88), Step 3.7 Flash: —

Writing & Preference benchmarks
Benchmark	DeepSeek-R1	Step 3.7 Flash
LMArena Text	1428	—
LMArena Creative Writing	1405	—
Short-Story Creative Writing	83%	—
EQ-Bench Creative Writing	1500	—
WildBench	82.8%	—
LMArena Multi-Turn	1405	—
LiveBench Language	48.5%	—

Frequently asked questions

Is DeepSeek-R1 better than Step 3.7 Flash?

Which is cheaper, DeepSeek-R1 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; DeepSeek-R1 lists at $0.50 and $2.15.

Is DeepSeek-R1 or Step 3.7 Flash better for coding?

DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 40.0 in the Noometry coding category.

Which has the bigger context window?

Step 3.7 Flash does, with 256K tokens against 164K.

How many benchmarks do DeepSeek-R1 and Step 3.7 Flash share?

3 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Step 3.7 Flash has 5.