Skip to content
Model Pareto

Step 5 Preview

StepFunProprietarystepfun.com ↗
Compare with nearest rivalsCompare with…
Input
$1.00/M tok
Output
$2.70/M tok
Blended
$1.425/M tok · 3:1
Speed
85tok/s
Context
1Mtokens

API-only preview; open weights scheduled for 2026-10-15. Writing: no LMArena/EQ-Bench entry or lab-reported writing benchmark as of 2026-09-24, so its Writing entry is fully estimated from its other categories (flagged “Estimated from other categories”).

Rankings

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench VerifiedEstimated
~#2 of 14 (estimated)~88.2%
  1. #1Claude Opus 596.0%
  2. ~#2Step 5 PreviewEstimated88.2%
  3. #2Claude Sonnet 585.2%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#5 of 19 (estimated)~70.2%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #4Claude Opus 579.2%
  4. ~#5Step 5 PreviewEstimated70.2%
  5. #5Intern-S2-397B68.5%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#2 of 20 (estimated)~92.1%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. ~#2Step 5 PreviewEstimated92.1%
  3. #2Qwen3.8 Flash-Next91.9%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#9 of 15 (estimated)~53.2
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #8GLM-5.353.6
  4. ~#9Step 5 PreviewEstimated53.2
  5. #9Kimi K351.9
No published score — estimated from related benchmarks

Writing & chatEstimated from other categories

IFBenchEstimated
~#3 of 126 (estimated)~82.7%
  1. #1MiniMax-M382.9%
  2. #2Qwen3.8 2.4T A95B82.8%
  3. ~#3Step 5 PreviewEstimated82.7%
  4. #3Qwen3.8-Omni-Flash81.5%
No published score — estimated from related benchmarks
MMMLUEstimated
~#2 of 5 (estimated)~91.2%
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Step 5 PreviewEstimated91.2%
  3. #2Gemma 4 31B88.4%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#9 of 54 (estimated)~1469 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #8GPT-5.51474
  4. ~#9Step 5 PreviewEstimated1469
  5. #9Qwen3.8 Max (0902)1467
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#13 of 54 (estimated)~1479 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #10MiMo-V2.6-Pro1480
  4. ~#13Step 5 PreviewEstimated1479
  5. #13DeepSeek V4.1 Flash1477
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#9 of 26 (estimated)~1972 Elo
  1. #1GPT-6 Astra2173
  2. #2Claude Fable 5.12162
  3. #8Grok 4.72007
  4. ~#9Step 5 PreviewEstimated1972
  5. #9Muse Spark 1.31906
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Step 5 PreviewEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#5 of 9 (estimated)~81.3%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #4Qwen3.8-Omni-Flash83.5%
  4. ~#5Step 5 PreviewEstimated81.3%
  5. #5Muse Glimmer78.8%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~88.1%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4Step 5 PreviewEstimated88.1%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
ChartographyEstimated
~#14 of 23 (estimated)~25.1%
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #13Gemini 3.1 Pro26.1%
  4. ~#14Step 5 PreviewEstimated25.1%
  5. #14Grok 4.620.5%
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#2 of 25 (estimated)~96.8%
  1. #1Inkling97.1%
  2. ~#2Step 5 PreviewEstimated96.8%
  3. #2Muse Glimmer94.7%
No published score — estimated from related benchmarks

Agents

τ²-bench (Telecom)Estimated
~#2 of 116 (estimated)~98.1%
  1. #1Step 3.7 Flash98.5%
  2. ~#2Step 5 PreviewEstimated98.1%
  3. #2Gemini 3.1 Pro95.6%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#3 of 12 (estimated)~82.3%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. ~#3Step 5 PreviewEstimated82.3%
  4. #3Nex-N2.5-Pro82.2%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Step 5 PreviewEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#17 of 89 (estimated)~38.6%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #16GPT-5.539.0%
  4. ~#17Step 5 PreviewEstimated38.6%
  5. #17Claude Sonnet 537.3%
No published score — estimated from related benchmarks