Data as of November 13, 2026 · How the score is built
Decision readingSarvam 30B scores 22 out of 100 and ranks #204 of 215. This profile shows 9 source-displayable benchmark rows; its strongest eligible category is Instruction Following at #148. Published weights can be self-hosted, but infrastructure cost varies and is not a comparable API token rate.
Email me when its price, rank or availability changes.
Capability
22/100
field median 49.4#204 of 215 ranked models
Public
#204of 215
Verified —
Price
Self-hosted; infrastructure cost varies
input median $0.60No comparable first-party hosted token rate
Speed
Not measured
field median 92 tok/sTime to first token not measured
Context
64Ktokens
field median 256,000Reported for this model; direct source link not stored
Decision snapshot
Where this model sits in the ranked field, its strongest published evidence, and what to validate before choosing it. The marker compares it with the current ranked catalog, not with an absolute quality threshold.
Strongest published evidence
Instruction Following ranks #148. A well-rounded choice across a range of tasks.
Validate before choosing
9 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 9 displayable benchmark rows
Is Sarvam 30B right for your job?
Its place on the LLM Selector’s job rankings, the same order the job pages publish. Describe your own job to see where it stands for that.
Where Sarvam 30B ranks by benchmark score:
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank Not rankedWeight 22%1 benchmarkVerified | 18.4 | 1 benchmark | Verified | |||
| CodingRank Not rankedWeight 20%2 benchmarksVerified | 25.2 | 2 benchmarks | Verified | |||
| ReasoningRank #153 of 160Percentile 4thWeight 17%1 benchmarkVerified | 19.9 | 1 benchmark | Verified | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeRank #157 of 180Percentile 13thWeight 12%2 benchmarksVerified | 26.4 | 2 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingRank #148 of 157Percentile 6thWeight 5%Not listedUnlisted sources | 28.8 | Not listed | Unlisted sources | |||
| MathWeight 5%3 benchmarksVerified | Score pending | 3 benchmarks | Verified |
9 of 919 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic1/1 verified
- Coding2/2 verified
- Reasoning1/1 verified
- MultimodalNot measured
- Knowledge2/2 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- Math3/3 verified
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
Sarvam 30B category percentile values
- AgenticNot eligible
- CodingNot eligible
- Reasoning4th percentile
- MultimodalNot eligible
- Knowledge13th percentile
- MultilingualNot eligible
- Instruction following6th percentile
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- AgenticNot ranked
- CodingNot ranked
- Reasoning#153/160
- MultimodalNot ranked
- Knowledge#157/180
- MultilingualNot ranked
- Inst. Following#148/157
- MathNot ranked
Benchmark ledger
Every result says who ran the test. For this model, Sarvam ran all 9. Coding opens by default. The tick marks the best source-verified result in the catalog; provisional leaders do not set the reference.
Coding2 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| HumanEvalEvaluating Large Language Models Trained on Code | 92.1% | Best verified: o4-mini · 97.3% | Gap5.2 behind | Reported by Sarvam | Shown only |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | 34% | Best verified: Claude Opus 5 · 96% | Gap62 behind | Reported by Sarvam | Shown only |
Agentic1 row
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| BrowseComp | 35.5% | Best verified: Atria Dawn Preview · 92.5% | Gap57 behind | Reported by Sarvam | Counts9% ref. weight |
Reasoning1 row
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| GPQA Diamond | 66.5% | Best verified: Sarvam 105B · 78.7% | Gap12.2 behind | Reported by Sarvam | Shown only |
Knowledge2 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| MMLU-ProMassive Multitask Language Understanding Professional | 80% | Best verified: Qwen3.7 Max · 89.6% | Gap9.6 behind | Reported by Sarvam | Counts6% ref. weight |
| MMLUMassive Multitask Language Understanding | 85.1% | Best verified: o1 · 91.8% | Gap6.7 behind | Reported by Sarvam | Shown only |
Math3 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| MATH-500MATH-500 Problem Set | 97% | Best verified: Ternary Bonsai 2 27B · 98.8% | Gap1.8 behind | Reported by Sarvam | Shown only |
| HMMT Feb 2025Harvard-MIT Mathematics Tournament February 2025 | 73.3% | Best verified: GLM-4.7 · 97.1% | Gap23.8 behind | Reported by Sarvam | Shown only |
| HMMT Nov 2025Harvard-MIT Mathematics Tournament November 2025 | 74.2% | Best verified: Qwen3.6 Plus · 94.6% | Gap20.4 behind | Reported by Sarvam | Shown only |
Outlined bars are lab-reported. Filled bars are benchmark-run or independent. Bars run 0–100; the dark tick marks the best source-verified value.
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 64K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- textsarvam-30b model card
- Output modalities
- textsarvam-30b model card
- Parameters
- Not sourced yet
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Established
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Sarvam 30B needs ~24GB VRAM (1× NVIDIA RTX 4090 (24GB)).
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
Sarvam 30B ranks #204 of 215 on the public leaderboard with a score of 21.95/100. It does not yet have enough sourced coverage for a verified position.
Sarvam 30B is a open weight model with a 64K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
9 of 919 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Instruction Following at #148, while its lowest eligible position is Knowledge at #157. a well-rounded choice across a range of tasks.
Last updated November 13, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Questions
How does Sarvam 30B perform overall in AI benchmarks?
Sarvam 30B ranks #204 out of 215 models on the public BenchAlign leaderboard, with a score of 21.95/100. Its evidence status is Estimated, and this profile shows 9 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Sarvam 30B good for knowledge and understanding?
Sarvam 30B ranks #157 out of 180 eligible models for knowledge and understanding, with a public category score of 26.4/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Sarvam 30B good for coding and programming?
Sarvam 30B has source-displayable benchmark coverage for coding and programming, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Sarvam 30B good for mathematics?
Sarvam 30B has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Sarvam 30B good for reasoning and logic?
Sarvam 30B ranks #153 out of 160 eligible models for reasoning and logic, with a public category score of 19.9/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Sarvam 30B good for agentic tool use and computer tasks?
Sarvam 30B has source-displayable benchmark coverage for agentic tool use and computer tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Sarvam 30B open source?
Sarvam 30B is an open-weight model from Sarvam. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Does Sarvam 30B have full benchmark coverage on BenchLM?
No. Sarvam 30B currently has 15 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Sarvam 30B?
Sarvam 30B has a reported context window of 64K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.