Model comparison

DeepSeek-R1 vs Step 3.5 Flash

DeepSeek-R1 and Step 3.5 Flash score almost the same on the Noometry Index (42.0 vs 41.7), so choose on price, context window or the category you care about most.

Last verified October 10, 2026. 17 shared benchmarks.

DeepSeek-R1

DeepSeek

42.0

Rank #110 Confirmed

Step 3.5 Flash

StepFun

41.7

Rank #116 Confirmed

Summary

They share 17 benchmarks with published results for both. DeepSeek-R1 scores higher in 6 categories and Step 3.5 Flash in 2 categories; 8 gaps are clear of the uncertainty.
The widest gap is in knowledge, where DeepSeek-R1 leads 44.3 to 39.0.
Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
Step 3.5 Flash accepts more context: 256K tokens versus 164K.
Step 3.5 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek-R1 and Step 3.5 Flash specifications
	DeepSeek-R1	Step 3.5 Flash
Provider	DeepSeek	StepFun
Noometry Index	42.0	41.7
Released	2025-01-20	2026-01-29
Weights	Proprietary	Open
Context window	164K	256K
Max output	64K	256K
Input $ / M tokens	$0.50	$0.10
Output $ / M tokens	$2.15	$0.30
Results tracked	52	19

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

Category by category

Coding DeepSeek-R1 leads

DeepSeek-R1: 45.9 (#63), Step 3.5 Flash: 41.7 (#106)

Coding benchmarks
Benchmark	DeepSeek-R1	Step 3.5 Flash
LMArena Coding	1427	1436
Aider Polyglot	71.4%	—
SciCode	35.7%	—
WeirdML	41.6%	—
LiveBench Coding	66.7%	—
ALE-Bench	804.12	—
AlgoTune	1.7	—

Agentic & Tool Use Not comparable

DeepSeek-R1: 30.4 (#68), Step 3.5 Flash: —

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-R1	Step 3.5 Flash
DeepResearch Bench	35.1%	—
BALROG	34.9%	—
METR Time Horizons	53.8%	—

Reasoning Step 3.5 Flash leads

DeepSeek-R1: 18.7 (#253), Step 3.5 Flash: 21.2 (#202)

Reasoning benchmarks
Benchmark	DeepSeek-R1	Step 3.5 Flash
LMArena Hard Prompts	1415	1411
ARC-AGI-2	1.3%	—
SimpleBench	40.8%	—
Kagi LLM Benchmark	69.4%	—
NYT Connections (extended)	—	28.4%
ARC-AGI-1	21.2%	—
CritPt	1.1%	—
LiveBench Reasoning	83.2%	—
LiveBench Data Analysis	69.8%	—
Epoch Capabilities Index	141.3	—
ForecastBench	60	—
LiveBench	71.6%	—

Math DeepSeek-R1 leads

DeepSeek-R1: 42.0 (#70), Step 3.5 Flash: 40.6 (#77)

Math benchmarks
Benchmark	DeepSeek-R1	Step 3.5 Flash
LMArena Math	1401	1408
MathArena Final-Answer Competitions	—	66.8%
OTIS Mock AIME 2024-2025	66.4%	—
Omni-MATH	42.4%	—
LiveBench Math	80.7%	—
MATH Level 5	96.6%	—

Knowledge DeepSeek-R1 leads

DeepSeek-R1: 44.3 (#81), Step 3.5 Flash: 39.0 (#127)

Knowledge benchmarks
Benchmark	DeepSeek-R1	Step 3.5 Flash
LMArena Expert	1394	1422
GPQA Diamond	76.3%	—
MMLU-Pro	79.3%	—
Confabulations	12.7%	—
Vectara Hallucination Rate	11.3%	—
GPQA (HELM)	66.6%	—

Multilingual DeepSeek-R1 leads

DeepSeek-R1: 52.6 (#80), Step 3.5 Flash: 50.7 (#115)

Multilingual benchmarks
Benchmark	DeepSeek-R1	Step 3.5 Flash
LMArena Non-English	1412	1386
LMArena Chinese	1443	1448
LMArena French	1415	1421
LMArena German	1405	1404
LMArena Japanese	1394	1353
LMArena Korean	1359	1350
LMArena Russian	1423	1385
LMArena Spanish	1410	1419

Instruction Following Step 3.5 Flash leads

DeepSeek-R1: 72.2 (#138), Step 3.5 Flash: 73.3 (#119)

Instruction Following benchmarks
Benchmark	DeepSeek-R1	Step 3.5 Flash
LMArena Instruction Following	1382	1385
LiveBench Instruction Following	80.5%	—
IFEval	78.4%	—

Long Context DeepSeek-R1 leads

DeepSeek-R1: 45.4 (#36), Step 3.5 Flash: 42.8 (#112)

Long Context benchmarks
Benchmark	DeepSeek-R1	Step 3.5 Flash
LMArena Longer Query	1391	1402
Fiction.LiveBench	75%	—

Writing & Preference DeepSeek-R1 leads

DeepSeek-R1: 61.5 (#84), Step 3.5 Flash: 59.0 (#108)

Writing & Preference benchmarks
Benchmark	DeepSeek-R1	Step 3.5 Flash
LMArena Text	1428	1403
LMArena Creative Writing	1406	1357
LMArena Multi-Turn	1404	1405
Short-Story Creative Writing	83%	—
EQ-Bench Creative Writing	1500	—
WildBench	82.8%	—
LiveBench Language	48.5%	—

Frequently asked questions

Is DeepSeek-R1 better than Step 3.5 Flash?

DeepSeek-R1 and Step 3.5 Flash score almost the same on the Noometry Index (42.0 vs 41.7), so choose on price, context window or the category you care about most.

Which is cheaper, DeepSeek-R1 or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.

Is DeepSeek-R1 or Step 3.5 Flash better for coding?

DeepSeek-R1 scores higher on coding benchmarks: 45.9 versus 41.7 in the Noometry coding category.

Which has the bigger context window?

Step 3.5 Flash does, with 256K tokens against 164K.

How many benchmarks do DeepSeek-R1 and Step 3.5 Flash share?

17 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Step 3.5 Flash has 19.