The AI arena is free today

Open Superagent

Ling 3.0 Flash vs Step 3.7 Flash

Ling 3.0 Flash and Step 3.7 Flash are closely matched at 36.4 and 30.2 on the LLM Stats Score. Ling 3.0 Flash is 4.9x cheaper per token.

InclusionAI · StepFun · Updated for 2026

Which is better?

Ling 3.0 Flash and Step 3.7 Flash are closely matched on the overall LLM Stats Score at 36.4 and 30.2.

The models split the 2 individual benchmarks reported for both models evenly.

On price, Ling 3.0 Flash is roughly 4.9x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Step 3.7 Flash also accepts a larger context window (262,144 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Ling 3.0 Flash

  • cost matters — it's about 4.9x cheaper per token
  • you want the most recent training data — it shipped Aug 2026

Choose Step 3.7 Flash

  • you process long inputs — it offers a 262,144 token context window
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Ling 3.0 Flash
InclusionAI
Step 3.7 Flash
StepFun
Core performance indexes
LLM Stats Score
36.4
#77
30.2
#120
Reasoning
35.6
#79
30.2
#117
Coding
25.3
#69
19.9
#99
Agents
19.5
#63
13.5
#92
Cost, coverage & limits
Benchmark wins
1 of 2
1 of 2
Input price
$0.06 / M
$0.20 / M
Output price
$0.18 / M
$1.15 / M
Context window
131,072
262,144

Individual benchmarks

19 reported for Ling 3.0 Flash · 4 for Step 3.7 Flash

2 shared

Ling 3.0 Flash outperforms in 1 benchmarks (SWE-Bench Pro), while Step 3.7 Flash is better at 1 benchmark (Terminal-Bench 2.1).

Both models are evenly matched across the benchmarks.

Sun Sep 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Ling 3.0 Flash costs less

For input processing, Ling 3.0 Flash ($0.06/1M tokens) is 3.3x cheaper than Step 3.7 Flash ($0.20/1M tokens).

For output processing, Ling 3.0 Flash ($0.18/1M tokens) is 6.4x cheaper than Step 3.7 Flash ($1.15/1M tokens).

In conclusion, Step 3.7 Flash is more expensive than Ling 3.0 Flash.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Sun Sep 20 2026 • llm-stats.com
InclusionAI
Ling 3.0 Flash
Input tokens$0.06
Output tokens$0.18
Best providerDeepinfra
StepFun
Step 3.7 Flash
Input tokens$0.20
Output tokens$1.15
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

74.0B diff

Step 3.7 Flash has 74.0B more parameters than Ling 3.0 Flash, making it 59.7% larger.

InclusionAI
Ling 3.0 Flash
124.0Bparameters
StepFun
Step 3.7 Flash
198.0Bparameters
124.0B
Ling 3.0 Flash
198.0B
Step 3.7 Flash

Context Window

Maximum input and output token capacity

Step 3.7 Flash accepts 262,144 input tokens compared to Ling 3.0 Flash's 131,072 tokens. Step 3.7 Flash can generate longer responses up to 262,144 tokens, while Ling 3.0 Flash is limited to 131,072 tokens.

InclusionAI
Ling 3.0 Flash
Input131,072 tokens
Output131,072 tokens
StepFun
Step 3.7 Flash
Input262,144 tokens
Output262,144 tokens
Sun Sep 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Step 3.7 Flash supports multimodal inputs, whereas Ling 3.0 Flash does not.

Step 3.7 Flash can handle both text and other forms of data like images, making it suitable for multimodal applications.

Ling 3.0 Flash

Text
Images
Audio
Video

Step 3.7 Flash

Text
Images
Audio
Video

Release Timeline

When each model was launched

Ling 3.0 Flash was released on 2026-08-04, while Step 3.7 Flash was released on 2026-06-10.

Ling 3.0 Flash is 2 months newer than Step 3.7 Flash.

Ling 3.0 Flash

Aug 4, 2026

1 months ago

1mo newer
Step 3.7 Flash

Jun 10, 2026

3 months ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

Ling 3.0 Flash is available from DeepInfra. Step 3.7 Flash is available from DeepInfra.

Ling 3.0 Flash

deepinfra logo
Deepinfra
Input Price:Input: $0.06/1MOutput Price:Output: $0.18/1M

Step 3.7 Flash

deepinfra logo
Deepinfra
Input Price:Input: $0.20/1MOutput Price:Output: $1.15/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Ling 3.0 Flash and Step 3.7 Flash side-by-side, then vote on the output you prefer.

Ling 3.0 Flash
✓ Preferred
Step 3.7 Flash
Open in Playground

FAQ

Common questions about Ling 3.0 Flash vs Step 3.7 Flash.

Which is better, Ling 3.0 Flash or Step 3.7 Flash?

Ling 3.0 Flash and Step 3.7 Flash are closely matched on the LLM Stats Score at 36.4 and 30.2. Ling 3.0 Flash is made by InclusionAI and Step 3.7 Flash is made by StepFun. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Ling 3.0 Flash compare to Step 3.7 Flash in benchmarks?

Ling 3.0 Flash scores AIME 2026: 93.2%, Multi-IF: 87.7%, HMMT Feb 26: 87.0%, IMO-AnswerBench: 83.7%, LiveCodeBench v6: 82.8%. Step 3.7 Flash scores Terminal-Bench 2.1: 59.5%, SWE-Bench Pro: 56.3%, Humanity's Last Exam (with tools, text-only): 47.2%, GDPval: 45.8%.

Is Ling 3.0 Flash cheaper than Step 3.7 Flash?

Ling 3.0 Flash is 3.3x cheaper for input tokens. Ling 3.0 Flash costs $0.06/M input and $0.18/M output via deepinfra. Step 3.7 Flash costs $0.20/M input and $1.15/M output via deepinfra.

What are the context window sizes for Ling 3.0 Flash and Step 3.7 Flash?

Ling 3.0 Flash supports 131K tokens and Step 3.7 Flash supports 262K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Ling 3.0 Flash and Step 3.7 Flash?

Key differences include LLM Stats Score (36.4 vs 30.2), context window (131K vs 262K), input pricing ($0.06 vs $0.20/M), multimodal support (no vs yes), licensing (Unknown vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Ling 3.0 Flash and Step 3.7 Flash?

Ling 3.0 Flash is developed by InclusionAI and Step 3.7 Flash is developed by StepFun.

Related comparisons