# Claude Opus 4.5 vs Sarvam 105B

> Side-by-side benchmark comparison for Claude Opus 4.5 and Sarvam 105B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-opus-4-5-vs-sarvam-105b
- Last updated: October 17, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Claude Opus 4.5 leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Claude Opus 4.5 has the higher overall point estimate 54.05 to 31.64. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in reasoning, where the averages are 78.3 for Claude Opus 4.5 and 25.9 for Sarvam 105B.
- The biggest single benchmark swing is SWE-bench Verified in Coding, with scores of 80.9% and 45%.
- Sarvam 105B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Claude Opus 4.5 also has the larger context window at 200K.

## Model Snapshot

| Property | Claude Opus 4.5 | Sarvam 105B |
|----------|----------|----------|
| Creator | Anthropic | Sarvam |
| Type | Proprietary | Open Weight |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 200K | 128K |
| Overall Score | 54.05 | 31.64 |
| Benchmarks Covered | 61 | 10 |
| Pricing (input/output) | $5.00 / $25.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Claude Opus 4.5 public-lane score: 32.3 (Estimated · #89/128)
- Sarvam 105B public-lane score: Coming soon

| Benchmark | Claude Opus 4.5 | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 59.3% | Coming soon | Coming soon |
| OSWorld-Verified | 66.3% | Coming soon | Coming soon |
| OSWorld | 66.3% | Coming soon | Coming soon |
| Claw-Eval | 59.6% | Coming soon | Coming soon |
| QwenClawBench | 52.3% | Coming soon | Coming soon |
| τ³-bench results | 70.2% | Coming soon | Coming soon |
| VITA-Bench | 23.3% | Coming soon | Coming soon |
| DeepPlanning | 26.4% | Coming soon | Coming soon |
| Toolathlon | 43.5% | Coming soon | Coming soon |
| MCP Atlas | 42.3% | Coming soon | Coming soon |
| MCP-Tasks | 71.8% | Coming soon | Coming soon |
| WideResearch | 76.4% | Coming soon | Coming soon |
| CyberGym | 50.6% | Coming soon | Coming soon |
| Gert Labs | 64.23% | Coming soon | Coming soon |
| JobBench | 32.3% | Coming soon | Coming soon |
| BrowseComp | Coming soon | 49.5% | Coming soon |

### Coding

- Winner: Not comparable
- Claude Opus 4.5 public-lane score: 40.3 (Estimated · #64/150)
- Sarvam 105B public-lane score: Coming soon

| Benchmark | Claude Opus 4.5 | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 80.9% | 45% | Claude Opus 4.5 |
| LiveCodeBench v6 | 84.8% | Coming soon | Coming soon |
| SWE-bench Pro | 57.1% | Coming soon | Coming soon |
| SWE Multilingual | 77.5% | Coming soon | Coming soon |
| NL2Repo | 43.2% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 59.3% | Coming soon | Coming soon |

### Reasoning

- Winner: Not comparable
- Claude Opus 4.5 public-lane score: 78.3 (Unranked · 4 rankable rows)
- Sarvam 105B public-lane score: 25.9 (Unranked · 3 rankable rows)

| Benchmark | Claude Opus 4.5 | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 64.4% | Coming soon | Coming soon |
| AI-Needle | 74% | Coming soon | Coming soon |
| GPQA Diamond | Coming soon | 78.7% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Claude Opus 4.5 public-lane score: 48.6 (#49/54)
- Sarvam 105B public-lane score: Coming soon

| Benchmark | Claude Opus 4.5 | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| MMMU | 80.7% | Coming soon | Coming soon |
| MMMU-Pro | 70.6% | Coming soon | Coming soon |
| RealWorldQA | 77.0% | Coming soon | Coming soon |
| OmniDocBench 1.5 | 87.7% | Coming soon | Coming soon |
| Video-MME (with subtitle) | 77.6% | Coming soon | Coming soon |
| Video-MME (w/o subtitle) | 81.4% | Coming soon | Coming soon |
| MathVision | 74.3% | Coming soon | Coming soon |
| We-Math | 70.0% | Coming soon | Coming soon |
| DynaMath | 79.7% | Coming soon | Coming soon |
| SimpleVQA | 65.7% | Coming soon | Coming soon |
| CharXiv | 68.5% | Coming soon | Coming soon |
| CountBench | 90.6% | Coming soon | Coming soon |
| AI2D_TEST | 87.7% | Coming soon | Coming soon |
| ERQA | 46.8% | Coming soon | Coming soon |
| VideoMMMU | 84.4% | Coming soon | Coming soon |
| MLVU (M-Avg) | 81.7% | Coming soon | Coming soon |
| ScreenSpot Pro | 45.7% | Coming soon | Coming soon |
| V* | 67.0% | Coming soon | Coming soon |

### Knowledge

- Winner: Directional only
- Claude Opus 4.5 public-lane score: 51.2 (Estimated · #77/184)
- Sarvam 105B public-lane score: 32.5 (Supported · #143/184)

| Benchmark | Claude Opus 4.5 | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 87% | Coming soon | Coming soon |
| SuperGPQA | 70.6% | Coming soon | Coming soon |
| MMLU-Pro | 89.5% | 81.7% | Claude Opus 4.5 |
| MMLU-Redux | 96.6% | Coming soon | Coming soon |
| C-Eval | 92.2% | Coming soon | Coming soon |
| HLE | 30.8% | Coming soon | Coming soon |
| MMLU | Coming soon | 90.6% | Coming soon |

### Multilingual

- Winner: Not comparable
- Claude Opus 4.5 public-lane score: 96.5 (#2/17)
- Sarvam 105B public-lane score: Coming soon

| Benchmark | Claude Opus 4.5 | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | 85.7% | Coming soon | Coming soon |
| NOVA-63 | 56.7% | Coming soon | Coming soon |
| INCLUDE | 86.2% | Coming soon | Coming soon |
| PolyMath | 79.0% | Coming soon | Coming soon |
| MAXIFE | 79.2% | Coming soon | Coming soon |

### Instruction Following

- Winner: Directional only
- Claude Opus 4.5 public-lane score: 31.9 (#131/148)
- Sarvam 105B public-lane score: 39.1 (#120/148)

| Benchmark | Claude Opus 4.5 | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 90.9% | 84.8% | Claude Opus 4.5 |
| IFBench | 58% | Coming soon | Coming soon |

### Mathematics

- Winner: Not comparable
- Claude Opus 4.5 public-lane score: 61.3 (#9/12)
- Sarvam 105B public-lane score: Coming soon

| Benchmark | Claude Opus 4.5 | Sarvam 105B | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 95.1% | Coming soon | Coming soon |
| HMMT Feb 2025 | 92.9% | 85.8% | Claude Opus 4.5 |
| HMMT Nov 2025 | 93.3% | 85.8% | Claude Opus 4.5 |
| HMMT Feb 2026 | 85.3% | Coming soon | Coming soon |
| MMAnswerBench | 84.0% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 34.386% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 4.878% | Coming soon | Coming soon |
| MATH-500 | Coming soon | 98.6% | Coming soon |
| AIME 2025 | Coming soon | 88.3% | Coming soon |

## FAQ

### Which is better overall, Claude Opus 4.5 or Sarvam 105B?

Claude Opus 4.5 has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Claude Opus 4.5 and Sarvam 105B?

The widest category gap is in reasoning, where the averages are 78.3 for Claude Opus 4.5 and 25.9 for Sarvam 105B.

### How many benchmarks does Claude Opus 4.5 cover on BenchLM?

Claude Opus 4.5 currently has 61 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 Opus 4.5 vs Claude Opus 4.5 Thinking](/compare/claude-opus-4-5-vs-claude-opus-4-5-thinking)
- [Sarvam 105B vs Claude Opus 4.5 Thinking](/compare/claude-opus-4-5-thinking-vs-sarvam-105b)
- [Claude Opus 4.5 vs Claude Opus 5.5](/compare/claude-opus-4-5-vs-claude-opus-5-5)
- [Sarvam 105B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-sarvam-105b)

## Explore More

- [Claude Opus 4.5 profile](/models/claude-opus-4-5)
- [Sarvam 105B profile](/models/sarvam-105b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)