Claude Sonnet 4.5 vs Sarvam 105B
Wins 5 of 6 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
Claude Sonnet 4.5 is the stronger all-rounder.Sarvam 105B is cheaper.
Scores updated · 21 tests both models report · How we compare
Where each one wins
Tests won in each of the six areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- ReasoningHard problems that need careful thinking30Claude Sonnet 4.53 of 3 tests
- CodingWriting and fixing software31Claude Sonnet 4.53 of 4 tests
- FactsGetting facts right instead of making them up20Claude Sonnet 4.52 of 2 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 4.51 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Sonnet 4.51 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 each
Long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Sarvam 105B costs 99% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude Sonnet 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+44.3points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+34.1points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+32.2points ahead
Where Sarvam 105B pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+25.4points ahead
- Recent programming contest problemsLiveCodeBench v6+7.7points ahead
Every test, side by side
All 21 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.5
- Terminal-Bench HardClaude Sonnet 4.5 by 34.135.61.5+34.1
- SWE-bench VerifiedClaude Sonnet 4.5 by 32.277.245+32.2
- SciCodeClaude Sonnet 4.5 by 19.345.726.4+19.3
- LiveCodeBench v6Sarvam 105B by 7.76471.7+7.7
AgentsEven
- BrowseCompSarvam 105B by 25.424.149.5+25.4
- GDPValClaude Sonnet 4.5 by 8.620.511.9+8.6
ReasoningClaude Sonnet 4.5
- GPQA DiamondClaude Sonnet 4.5 by 9.683.473.8+9.6
- Humanity's Last ExamClaude Sonnet 4.5 by 6.817.811+6.8
- CritPtClaude Sonnet 4.5 by 1.11.10+1.1
FactsClaude Sonnet 4.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 44.350.96.6+44.3
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 15.332.917.6+15.3
Following instructionsClaude Sonnet 4.5
- IFBenchClaude Sonnet 4.5 by 22.957.334.4+22.9
Other results8 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- AA-OmniscienceClaude Sonnet 4.5 by 59.3-0.1-59.4+59.3
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 42.352.19.8+42.3
- τ²-Bench Telecom (AA run)Claude Sonnet 4.5 by 31.378.146.8+31.3
- AA IntelligenceClaude Sonnet 4.5 by 11.920.78.8+11.9
- HMMT 2025Sarvam 105B by 11.274.685.8+11.2
- AIME 2025Sarvam 105B by 9.78796.7+9.7
- AA Agentic IndexSarvam 105B by 7.217.524.7+7.2
- MMLU-ProClaude Sonnet 4.5 by 5.887.581.7+5.8
Questions people ask
Which is better, Claude Sonnet 4.5 or Sarvam 105B?
Claude Sonnet 4.5 wins five of the six areas where both have results: coding, reasoning, facts, long documents and following instructions. Sarvam 105B wins none, but costs 99% less. They are level on agents.
Which is better for coding?
Claude Sonnet 4.5. It wins 3 of the 4 coding tests both models report; Sarvam 105B wins 1.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; Sarvam 105B costs $0.04 and $0.17. That makes Sarvam 105B about 99% cheaper for the same work.
How do you compare the two?
We use the 21 benchmark tests both models have published scores on. The verdict counts the 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.