readable AI benchmarks (simplified)
Sarvam
Sarvam 30B (High)
Sarvam 30B (High) has a Quality Score of 12.2, ranking 530th among 572 scored models. Per 1M tokens, pricing is $0.026 input, $0.110 output, and $0.016 cached input. It accepts text input, outputs text, and has a 65,536 token context window. Its Reliability Score is 14.2, ranking 537th among 574 scored models, below average (total average: 36.5). Its Value Score is 11.7, low compared with the total Value average of 31.5.
Quality Score12.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score11.7
Factual reliability14.2
Cache Discount38%
Model specification
- Reasoning
- reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 65,536 tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.026
- Output
- $0.110
- Cached Input
- $0.016
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 6.6
- Coding
- not available
- Agentic
- not available
- Omniscience
- -71.5
- Correct
- 12.6%
- Blended price
- $0.027
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 96.7%
Correct 12.6%Incorrect 84.1%Partial / not attempted 3.3%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 8%
- GPQA Diamond
- 63%
- CritPt
- 0%
- AA-Omniscience
- 14%
- AA-LCR
- 0%
Similar models
- Sarvam M (Reasoning, Based on Mistral Small 3.1)SarvamQuality Score 13.7Value Score not available
- Sarvam 105B (High)SarvamQuality Score 16.9Value Score 16.0
- Sarvam MSarvamQuality Score not availableValue Score not available
- Olmo 3 7B ThinkAllen Institute for AIQuality Score 11.4Value Score not available
- Reka Flash 3Reka AIQuality Score 13.1Value Score not available
- Qwen3 VL 4B (Reasoning)AlibabaQuality Score 13.3Value Score not available