AI BENCHY
Advertise here
#63

Step 3.7 Flash

Stepfun Release: 2026-05-29 Tested on: 2026-07-16 22:46 stepfun/step-3.7-flash::low
198B total (11B active)MoEOpen source
(high) (medium) (low)

Summary

Step 3.7 Flash scores 7.3 on AI BENCHY and ranks #63. It has 10.0 reliability, a 68.2% pass rate, $0.454 total cost, and 20.68s average response time.

Model facts

Researched on 2026-08-12

Reported
Parameters
198B total (11B active)
Architecture
MoE
Availability
Open source
License
Apache-2.0

Includes the vendor-reported vision component in the total.

Parameter source Availability source

Score

7.3

Consistency

8.1

Reliability

10.0

Total Cost (Current Price)

$0.454

Total Output Tokens

376,581

Total Input Tokens

103,833

Input Price

$0.200 / 1M

Output Price

$1.150 / 1M

Tests Correct

Wrong Tests: 10

Attempt pass rate: 68.2%

Flaky tests

5

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

20.68s

Response Time (max): 124.75s

Response Time (total): 455.01s

Wrong answer: 8 Invalid tool call: 1 No answer: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#63 Step 3.7 Flash

low
Invalid SVG
Cost
$0.004
Time
25.3s
Tokens
3,072 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 02:29 Re-test 7.1 10.0 $0.390 Compare
2026-07-16 22:46 New test added 7.3 10.0 $0.454 Current run
2026-06-04 13:49 New test added 7.3 10.0 $0.341 Compare
2026-05-29 11:49 Initial run 7.4 10.0 $0.336 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-07-16 22:46 · New test added66/66 attempts7.38.110.012/225376,581103,833$0.45420.68s
2026-06-04 13:49 · New test added63/63 attempts7.38.410.012/214289,32540,101$0.34115.74s
Difference—0.0-0.30.00+1+87256+63732+$0.114+4938ms

Benchmark coverage differs: 66/66 attempts (Target: 3 repeats per test) versus 63/63 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-06-04 15:40 $0.200 / 1M $1.150 / 1M

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Step 3.7 FlashlowvsMuse Glimmer 30BlowStep 3.7 FlashlowvsSolar Pro 4highStep 3.7 FlashlowvsQwen3.5-122B-A10BmediumStep 3.7 FlashlowvsGrok 4.3mediumStep 3.7 FlashlowvsMuse Glimmer 30BmediumStep 3.7 FlashlowvsGPT-5.6 SolnoneStep 3.7 FlashlowvsQwen3.7 FlashlowStep 3.7 FlashlowvsDeepSeek V3.2mediumStep 3.7 FlashlowvsQwen3.5 Plus 2026-04-20mediumStep 3.7 FlashlowvsGLM 5.1medium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.7 7.9
Coding 8.2 7.2
Combined 7.3 5.8
Data parsing and extraction 7.3 5.8
Domain specific 5.3 7.2
General Intelligence 3.4 9.3
Instructions following 9.8 10.0
Puzzle Solving 5.5 9.9
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models