The AI arena is free today

Open Superagent

Sarvam-105B vs Step-3.5-Flash

Step-3.5-Flash leads the LLM Stats Score 37.2 to 25.7.

Sarvam AI · StepFun · Updated for 2026

Which is better?

Step-3.5-Flash leads the overall LLM Stats Score 37.2 to 25.7, ranking #72 overall.

In the 4 individual benchmarks reported for both models, Step-3.5-Flash wins 4; this is a narrower head-to-head signal than the composite indexes.

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

Choose Sarvam-105B

  • you want the most recent training data — it shipped Mar 2026

Choose Step-3.5-Flash

  • overall performance matters — it scores 37.2 and ranks #72 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 4 of 4 exact shared results

At a glance

The differences that matter most.

Sarvam-105B
Sarvam AI
Step-3.5-Flash
StepFun
Core performance indexes
LLM Stats Score
25.7
#157
37.2
#72
Reasoning
26.2
#151
37.2
#72
Coding
-1.6
#251
20.5
#99
Agents
5.5
#148
15.3
#88
Cost, coverage & limits
Benchmark wins
0 of 4
4 of 4
Input price
— / M
$0.10 / M
Output price
— / M
$0.40 / M
Context window
—
65,536

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Sarvam-105B
Step-3.5-Flash
Math
29.1#88
33.9#50
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

14 reported for Sarvam-105B · 7 for Step-3.5-Flash

4 shared

Sarvam-105B outperforms in 0 benchmarks, while Step-3.5-Flash is better at 4 benchmarks (AIME 2025, BrowseComp, LiveCodeBench v6, SWE-Bench Verified).

Step-3.5-Flash significantly outperforms across most benchmarks.

Tue Sep 22 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

91.0B diff

Step-3.5-Flash has 91.0B more parameters than Sarvam-105B, making it 86.7% larger.

Sarvam AI
Sarvam-105B
105.0Bparameters
StepFun
Step-3.5-Flash
196.0Bparameters
105.0B
Sarvam-105B
196.0B
Step-3.5-Flash

Context Window

Maximum input and output token capacity

Only Step-3.5-Flash specifies input context (65,536 tokens). Only Step-3.5-Flash specifies output context (8,192 tokens).

Sarvam AI
Sarvam-105B
Input- tokens
Output- tokens
StepFun
Step-3.5-Flash
Input65,536 tokens
Output8,192 tokens
Tue Sep 22 2026 • llm-stats.com

License

Usage and distribution terms

Both models are licensed under Apache 2.0.

Both models share the same licensing terms, providing consistent usage rights.

Sarvam-105B

Apache 2.0

Open weights

Step-3.5-Flash

Apache 2.0

Open weights

Release Timeline

When each model was launched

Sarvam-105B was released on 2026-03-06, while Step-3.5-Flash was released on 2026-02-02.

Sarvam-105B is 1 month newer than Step-3.5-Flash.

Sarvam-105B

Mar 6, 2026

6 months ago

1mo newer
Step-3.5-Flash

Feb 2, 2026

7 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

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Sarvam-105B and Step-3.5-Flash side-by-side, then vote on the output you prefer.

Sarvam-105B
✓ Preferred
Step-3.5-Flash
Open in Playground

FAQ

Common questions about Sarvam-105B vs Step-3.5-Flash.

Which is better, Sarvam-105B or Step-3.5-Flash?

Step-3.5-Flash leads the LLM Stats Score 37.2 to 25.7. Sarvam-105B is made by Sarvam AI and Step-3.5-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 Sarvam-105B compare to Step-3.5-Flash in benchmarks?

Sarvam-105B scores MATH-500: 98.6%, AIME 2025: 96.7%, MMLU: 90.6%, HMMT 2025: 85.8%, HMMT25: 85.8%. Step-3.5-Flash scores AIME 2025: 97.3%, Tau-bench: 88.2%, LiveCodeBench v6: 86.4%, IMO-AnswerBench: 85.4%, SWE-Bench Verified: 74.4%.

What are the context window sizes for Sarvam-105B and Step-3.5-Flash?

Sarvam-105B supports an unknown number of tokens and Step-3.5-Flash supports 66K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Sarvam-105B and Step-3.5-Flash?

Key differences include LLM Stats Score (25.7 vs 37.2). See the full comparison above for benchmark-by-benchmark results.

Who makes Sarvam-105B and Step-3.5-Flash?

Sarvam-105B is developed by Sarvam AI and Step-3.5-Flash is developed by StepFun.

Related comparisons