# Claude 3.5 Haiku vs Sarvam 105B

> Side-by-side benchmark comparison for Claude 3.5 Haiku and Sarvam 105B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-3-5-haiku-vs-sarvam-105b
- Last updated: October 14, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Claude 3.5 Haiku leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Claude 3.5 Haiku has the higher overall point estimate 47 to 31.53. Conditional score ranges do not establish rank confidence.
- The biggest single benchmark swing is MMLU-Pro in Knowledge, with scores of 65% and 81.7%.
- Claude 3.5 Haiku also has the larger context window at 200K.

## Model Snapshot

| Property | Claude 3.5 Haiku | Sarvam 105B |
|----------|----------|----------|
| Creator | Anthropic | Sarvam |
| Type | Proprietary | Open Weight |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 200K | 128K |
| Overall Score | null | 31.53 |
| Benchmarks Covered | 10 | 10 |
| Pricing (input/output) | N/A | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Claude 3.5 Haiku public-lane score: Coming soon
- Sarvam 105B public-lane score: Coming soon

| Benchmark | Claude 3.5 Haiku | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| BrowseComp | Coming soon | 49.5% | Coming soon |

### Coding

- Winner: Not comparable
- Claude 3.5 Haiku public-lane score: Coming soon
- Sarvam 105B public-lane score: Coming soon

| Benchmark | Claude 3.5 Haiku | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| HumanEval | 88.1% | Coming soon | Coming soon |
| SWE-bench Verified | 40.6% | 45% | Sarvam 105B |

### Reasoning

- Winner: Not comparable
- Claude 3.5 Haiku public-lane score: Coming soon
- Sarvam 105B public-lane score: 25.9 (Unranked · 3 rankable rows)

| Benchmark | Claude 3.5 Haiku | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| BBH | 86.6% | Coming soon | Coming soon |
| DROP | 83.1% | Coming soon | Coming soon |
| GPQA Diamond | Coming soon | 78.7% | Coming soon |

### Knowledge

- Winner: Not comparable
- Claude 3.5 Haiku public-lane score: Coming soon
- Sarvam 105B public-lane score: 32.9 (Supported · #140/181)

| Benchmark | Claude 3.5 Haiku | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 41.6% | Coming soon | Coming soon |
| MMLU-Pro | 65% | 81.7% | Sarvam 105B |
| MMLU | 80.3% | 90.6% | Sarvam 105B |

### Multilingual

- Winner: Not comparable
- Claude 3.5 Haiku public-lane score: Coming soon
- Sarvam 105B public-lane score: Coming soon

| Benchmark | Claude 3.5 Haiku | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| MGSM | 85.6% | Coming soon | Coming soon |

### Instruction Following

- Winner: Not comparable
- Claude 3.5 Haiku public-lane score: Coming soon
- Sarvam 105B public-lane score: 39.1 (#107/128)

| Benchmark | Claude 3.5 Haiku | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 85.9% | 84.8% | Claude 3.5 Haiku |

### Mathematics

- Winner: Not comparable
- Claude 3.5 Haiku public-lane score: Coming soon
- Sarvam 105B public-lane score: Coming soon

| Benchmark | Claude 3.5 Haiku | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| AIME 2024 | 5.3% | Coming soon | Coming soon |
| MATH-500 | Coming soon | 98.6% | Coming soon |
| AIME 2025 | Coming soon | 88.3% | Coming soon |
| HMMT Feb 2025 | Coming soon | 85.8% | Coming soon |
| HMMT Nov 2025 | Coming soon | 85.8% | Coming soon |

## FAQ

### Which is better overall, Claude 3.5 Haiku or Sarvam 105B?

Claude 3.5 Haiku has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### How many benchmarks does Claude 3.5 Haiku cover on BenchLM?

Claude 3.5 Haiku currently has 10 sourced benchmark scores on BenchLM.

### How many benchmarks does Sarvam 105B cover on BenchLM?

Sarvam 105B currently has 10 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Claude 3.5 Haiku vs Claude Opus 5.5](/compare/claude-3-5-haiku-vs-claude-opus-5-5)
- [Sarvam 105B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-sarvam-105b)
- [Claude 3.5 Haiku vs GPT-6.1 Sol](/compare/claude-3-5-haiku-vs-gpt-6-1-sol)
- [Sarvam 105B vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-sarvam-105b)

## Explore More

- [Claude 3.5 Haiku profile](/models/claude-3-5-haiku)
- [Sarvam 105B profile](/models/sarvam-105b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)