Model vs model
Ling 3.1 Flash vs Step 3.7 Flash
Both Ling 3.1 Flash and Step 3.7 Flash are open-weight models with context windows of about 256K tokens. The difference that decides it is quality: Ling 3.1 Flash scores 43.9 on the Intelligence Index against 19.5, at nearly the same blended price of $0.45 and $0.44 per 1M tokens. Pick Ling 3.1 Flash for hard reasoning and long documents, and Step 3.7 Flash when you need image input.
At a glance
Longer bar means the bigger number.
Blended price · per 1M tokens, lower is better
Intelligence Index · Artificial Analysis, higher is better
Where they sit among all 44 models
Ling 3.1 Flash ranks 12th of the 43 models with an Intelligence Index, Step 3.7 Flash 32nd. Up and to the left is smarter for less money. Hover or tap a dot for its numbers, then click it to compare that model with Ling 3.1 Flash.
Which one to pick
Pick Ling 3.1 Flash if
- you want the higher overall score (43.9 vs 19.5)
- you care about Humanity's Last Exam (hard reasoning): 43.5 vs 21.4
- you care about SciCode (scientific coding): 56.8 vs 43.9
Pick Step 3.7 Flash if
- you want the lower bill ($0.44 vs $0.45 per 1M tokens blended)
- you need to send images
How smart is each one?
Of the 4 scores both models have, Ling 3.1 Flash is ahead on every one.
Every intelligence score we have
Out of 100, higher is better. Ling 3.1 Flash Step 3.7 Flash
Overall
Intelligence Index
43.919.5
By area
Coding
39.6Ling 3.1 Flash: not scored yet
By field of work
Finance & accounting
45.5Step 3.7 Flash: not scored yet
Legal
41.6Step 3.7 Flash: not scored yet
Economics
49.9Step 3.7 Flash: not scored yet
Engineering
44.3Step 3.7 Flash: not scored yet
Strategy & operations
47.9Step 3.7 Flash: not scored yet
Benchmarks
Hard reasoning · Humanity's Last Exam
43.521.4Science · GPQA Diamond
80.9Ling 3.1 Flash: not scored yet
Scientific coding · SciCode
56.843.9Terminal tasks · Terminal-Bench 4.0
32.8Step 3.7 Flash: not scored yet
Tool use · τ-Bench Banking
12Ling 3.1 Flash: not scored yet
Instruction following · IFBench
67.3Ling 3.1 Flash: not scored yet
Long documents · AA-LCR
82.373.7
The specs
| Spec | Ling 3.1 Flash | Step 3.7 Flash |
|---|---|---|
| Input price | $0.30 per 1M | $0.20 per 1M |
| Output price | $0.90 per 1M | $1.15 per 1M |
| Cost per test task | Not tested | Not tested |
| Context window | 262K | 256K |
| Max output | 33K | 256K |
| Accepts | Text | Text, Image |
| Open weights | Yes | Yes |
| Lab | InclusionAI | StepFun |
| Released | Sep 2026 | May 2026 |
| Knowledge cutoff | Not published | Mar 2026 |
Blended price weighs 3 parts input to 1 part output. List prices from models.dev.
Questions
Is Ling 3.1 Flash or Step 3.7 Flash cheaper?
Step 3.7 Flash is cheaper. It charges $0.20 per 1M input tokens and $1.15 per 1M output tokens, against $0.30 and $0.90 for Ling 3.1 Flash. Blended 3 parts input to 1 part output, that is $0.44 against $0.45 per 1M tokens.
Which is smarter, Ling 3.1 Flash or Step 3.7 Flash?
Ling 3.1 Flash scores higher on the Artificial Analysis Intelligence Index, 43.9 against 19.5 for Step 3.7 Flash. The biggest differences are on Humanity's Last Exam (43.5 vs 21.4) and SciCode (56.8 vs 43.9).
Which has the longer context window?
They are about the same: Ling 3.1 Flash accepts 262K tokens and Step 3.7 Flash 256K.
Can I compare Ling 3.1 Flash and Step 3.7 Flash on my own prompt?
Yes. ModelCompare sends one prompt to both models at once and shows each answer side by side with what it cost. You can try it free without an account.
Related comparisons
Where the numbers come from
Intelligence Index and benchmark scores are from Artificial Analysis, at each model’s highest effort, except SimpleQA, which is from Epoch AI, and the Uncensored score, which is from the UGI Leaderboard. The hallucination test is ours: questions with one exact answer, fake evidence pushed against right answers and requests that tempt a model to name packages that don’t exist. Prices are list prices from models.dev. Example answers come from our own test runs. Updated October 25, 2026.