DeepSeek-V3 vs Sarvam 30B
Wins 4 of 6 areas
Coding · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
DeepSeek-V3 is the stronger all-rounder.Sarvam 30B is cheaper.
Scores updated · 22 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.
- CodingWriting and fixing software31DeepSeek-V33 of 4 tests
- FactsGetting facts right instead of making them up20DeepSeek-V32 of 2 tests
- Long documentsFinding answers in very long texts10DeepSeek-V31 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V31 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
Agents, 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 30B costs 88% 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 DeepSeek-V3 pulls ahead
- Code for real scientific research problemsSciCode+19.8points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+14.5points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+12.9points ahead
Where Sarvam 30B pulls ahead
- Recent programming contest problemsLiveCodeBench v6+23.1points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+2.8points ahead
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3
- LiveCodeBench v6Sarvam 30B by 23.146.970+23.1
- SciCodeDeepSeek-V3 by 19.83919.2+19.8
- Terminal-Bench HardDeepSeek-V3 by 12.915.22.3+12.9
- SWE-bench VerifiedDeepSeek-V3 by 84234+8
ReasoningEven
- Humanity's Last ExamSarvam 30B by 2.84.77.5+2.8
- GPQA DiamondDeepSeek-V3 by 2.265.563.3+2.2
- CritPttie00.3tie
FactsDeepSeek-V3
- AA-Omniscience · AccuracyDeepSeek-V3 by 12.925.412.6+12.9
- AA-Omniscience · Non-hallucinationDeepSeek-V3 by 10.414.13.7+10.4
Following instructionsDeepSeek-V3
- IFBenchDeepSeek-V3 by 14.54126.5+14.5
Other results10 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.
- HMMT 2025Sarvam 30B by 46.727.574.2+46.7
- AIME 2025Sarvam 30B by 45.451.396.7+45.4
- AA-OmniscienceDeepSeek-V3 by 30.8-40.7-71.5+30.8
- HumanEvalSarvam 30B by 26.965.292.1+26.9
- MBPPSarvam 30B by 17.375.492.7+17.3
- Artificial Analysis Coding IndexDeepSeek-V3 by 15.1237.9+15.1
- τ²-Bench Telecom (AA run)DeepSeek-V3 by 12.647.134.5+12.6
- MATH-500 (EM)Sarvam 30B by 6.890.297+6.8
- MMLU-ProSarvam 30B by 4.175.980+4.1
- AA IntelligenceDeepSeek-V3 by 3.19.76.6+3.1
Questions people ask
Which is better, DeepSeek-V3 or Sarvam 30B?
DeepSeek-V3 wins four of the six areas where both have results: coding, facts, long documents and following instructions. Sarvam 30B wins none, but costs 88% less. They are level on agents and reasoning.
Which is better for coding?
DeepSeek-V3. It wins 3 of the 4 coding tests both models report; Sarvam 30B wins 1.
Which is cheaper?
DeepSeek-V3 costs $0.24 per million input tokens and $0.90 per million output tokens; Sarvam 30B costs $0.03 and $0.11. That makes Sarvam 30B about 88% cheaper for the same work.
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.