Sarvam 105B
SarvamOpen weightsReasoningProvisionalReleased Mar 6, 2026
Overall score
31.7
Rank 177 of 222 · 17.3–46.0
Context window
128K
128,000 tokens
Price per 1M tokens
Free in · Free out
Source: BenchLM
Blended price
Free
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Knowledge67.6
- 2Instruction following#12039.1
- 3Agentic & tool use25.3
- 4Reasoning25.0
- 5Coding24.5
Benchmark results (9)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Math
| AIME 2025 | 88.3 | #16 of 38 |
| MATH-500 | 98.6 | #2 of 20 |
| HMMT Feb 2025 | 85.8 | #11 of 13 |
| HMMT Nov 2025 | 85.8 | #10 of 12 |
Knowledge
| MMLU-Pro | 81.7 | #32 of 67 |
| MMLU | 90.6 | #4 of 28 |
Agentic & tool use
| BrowseComp | 49.5 | #45 of 50 |
Coding
| SWE-bench Verified | 45.0 | #92 of 98 |
Instruction following
| IFEval | 84.8 | #33 of 53 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price (BenchLM) | Free | Free | — |
Sarvam's official API pricing page lists Sarvam 105B as free per token.
Speed
Measured by us through OpenRouter (median of trials).
Not available on OpenRouter, so we cannot measure it yet.
Related models
Same family
- Sarvam 30B28.6
Similar score
- Ornith-1.5-9B31.7 · —
- DeepSeek V331.9 · $0.48
- LFM2.5-2.6B31.2 · —
- Nemotron 3 Nano Omni 30B A3B32.2 · —
- Gemma 4 E4B31.1 · —