MiMo V2 Flash vs Sarvam 105B
Wins 5 of 6 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
MiMo V2 Flash is the stronger all-rounder.Sarvam 105B 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 software40MiMo V2 Flash4 of 4 tests
- ReasoningHard problems that need careful thinking30MiMo V2 Flash3 of 3 tests
- FactsGetting facts right instead of making them up10MiMo V2 Flash1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10MiMo V2 Flash1 of 1 test
- Following instructionsDoing exactly what it is asked10MiMo V2 Flash1 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 47% 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 MiMo V2 Flash pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+29.8points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+28.4points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+26.5points ahead
Where Sarvam 105B pulls ahead
- Real work tasks from 44 professionsGDPVal+5.3points 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.
CodingMiMo V2 Flash
- SWE-bench VerifiedMiMo V2 Flash by 28.473.445+28.4
- Terminal-Bench HardMiMo V2 Flash by 26.5281.5+26.5
- SciCodeMiMo V2 Flash by 1339.426.4+13
- LiveCodeBench v6MiMo V2 Flash by 8.980.671.7+8.9
AgentsEven
- BrowseCompMiMo V2 Flash by 8.858.349.5+8.8
- GDPValSarvam 105B by 5.36.611.9+5.3
ReasoningMiMo V2 Flash
- Humanity's Last ExamMiMo V2 Flash by 11.822.811+11.8
- GPQA DiamondMiMo V2 Flash by 10.884.673.8+10.8
- CritPtMiMo V2 Flash by 4.34.30+4.3
FactsMiMo V2 Flash
- AA-Omniscience · AccuracyMiMo V2 Flash by 7.224.817.6+7.2
- AA-Omniscience · Non-hallucinationtie6.66.6tie
Following instructionsMiMo V2 Flash
- IFBenchMiMo V2 Flash by 29.864.234.4+29.8
Other results9 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.
- τ²-Bench Telecom (AA run)MiMo V2 Flash by 48.29546.8+48.2
- Artificial Analysis Coding IndexMiMo V2 Flash by 4049.89.8+40
- Arena-Hard-V2MiMo V2 Flash by 15.286.271+15.2
- AA-OmniscienceMiMo V2 Flash by 14.1-45.4-59.4+14.1
- AA Agentic IndexSarvam 105B by 12.71224.7+12.7
- AA IntelligenceMiMo V2 Flash by 1220.88.8+12
- MMLU-ProMiMo V2 Flash by 3.284.981.7+3.2
- AIME 2025Sarvam 105B by 2.694.196.7+2.6
- HMMT 2025Sarvam 105B by 1.484.485.8+1.4
Questions people ask
Which is better, MiMo V2 Flash or Sarvam 105B?
MiMo V2 Flash wins five of the six areas where both have results: coding, reasoning, facts, long documents and following instructions. Sarvam 105B wins none, but costs 47% less. They are level on agents.
Which is better for coding?
MiMo V2 Flash. It wins 4 of the 4 coding tests both models report; Sarvam 105B wins none.
Which is cheaper?
MiMo V2 Flash costs $0.10 per million input tokens and $0.30 per million output tokens; Sarvam 105B costs $0.04 and $0.17. That makes Sarvam 105B about 47% 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 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.