SarvamSarvam 105B
Sarvam 105B is a Sarvam open-weights reasoning model, released 6 Mar 2026. Its best configuration (high reasoning effort) ranks #663 of 785 on the BenchLeader Index at 40.1 ±4.5, in the lower half. The ± is the point: 272 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in reasoning (41) and lowest in long context (23). At $0.073 per million tokens blended it is among the cheapest fifth of ranked models. Output speed of 197 tokens per second puts it in the fastest quarter, with a first answer in 11.8 s. Last measured 6 Mar 2026.stale: no new result in six months
- Blended price
- $0.073/M
- $0.040 in · $0.170 out
- Output speed
- 197 tok/s
- measured by Artificial Analysis
- First answer
- 12 s
- Context
- 128k
- Full answer
- 14 s
- median, reasoning included
- Cost per run
- –
- Released
- 6 Mar 2026
- Overall index40
- Reasoning41
- Agents & tools35
- Knowledge35
- Instruction following38
- Long context23
- Composite39
How its index has moved
19 Sept 2026 to 21 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | high | Source |
|---|---|---|
| GPQA Diamond (AA)not in index | 73.8%#263 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 11.0%#302 | Artificial Analysis |
| CritPt | 0.0%#315 | Artificial Analysis |
Agents & tools
| Benchmark | high | Source |
|---|---|---|
| Terminal-Bench Hard | 1.5%#338 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 46.8%#204 | Artificial Analysis |
Knowledge
| Benchmark | high | Source |
|---|---|---|
| AA-Omniscience | -59.4#462 | Artificial Analysis |
| AA-Omniscience: accuracynot in index | 17.6%#362 | Artificial Analysis |
| AA-Omniscience: non-hallucinationnot in index | 6.6%#504 | Artificial Analysis |
Instruction following
| Benchmark | high | Source |
|---|---|---|
| IFBench | 34.4%#319 | Artificial Analysis |
Long context
| Benchmark | high | Source |
|---|---|---|
| AA-LCR | 0.0%#493 | Artificial Analysis |
Composite
| Benchmark | high | Source |
|---|---|---|
| AA Intelligence Index v4.3.2 | 8.8#426 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0001 | – | 13.3 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0006 | – | 14.8 s |
| Code edit | 6,000 / 1,500 | $0.0005 | – | 19.4 s |
| Agentic coding session | 60,000 / 4,000 | $0.0031 | – | 32.0 s |
| Structured extraction | 2,000 / 200 | $0.0001 | – | 12.8 s |
More from Sarvam
See also
Questions people ask
- What are Sarvam 105B's benchmark scores?
- As of 24 Oct 2026, Sarvam 105B (high effort) scores 40.1 ±4.5 on the BenchLeader Index, strongest in reasoning (41) and weakest in long context (23). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
- How does Sarvam 105B rank?
- Sarvam 105B (high effort) is #663 of 785 ranked configurations on 24 Oct 2026. 272 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Sarvam 105B cost per 1M tokens?
- As of 24 Oct 2026, Sarvam 105B costs $0.040 per 1M input tokens and $0.170 per 1M output tokens, $0.073 blended (three input tokens per output token).
- When was Sarvam 105B released?
- Sarvam released Sarvam 105B on 6 Mar 2026.
Data as of 24 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Sarvam 105B: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/sarvam-105b.