Claude Sonnet 4 vs MiniMax M2
Wins 3 of 6 areas
Coding · Facts · Long documents
Wins 3 of 6 areas
Agents · Reasoning · Following instructions
The two are evenly matched.Claude Sonnet 4 is better at coding and facts; MiniMax M2 at agents and reasoning.
Scores updated · 31 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 software30Claude Sonnet 43 of 4 tests · 1 tie
- FactsGetting facts right instead of making them up10Claude Sonnet 41 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude Sonnet 41 of 1 test
- AgentsCarrying out multi-step tasks on its own02MiniMax M22 of 2 tests
- ReasoningHard problems that need careful thinking01MiniMax M21 of 3 tests · 2 ties
- Following instructionsDoing exactly what it is asked01MiniMax M21 of 1 test
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.
MiniMax M2 costs 92% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+61.8points ahead
- Reasons across sets of long documentsAA-LCR+6points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+5.3points ahead
Where MiniMax M2 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+31.8points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+17.6points ahead
- Real work tasks from 44 professionsGDPVal+16.9points ahead
Every test, side by side
All 31 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4
- Terminal-Bench HardClaude Sonnet 4 by 5.331.125.8+5.3
- SciCodeClaude Sonnet 4 by 3.94036.1+3.9
- SWE-bench VerifiedClaude Sonnet 4 by 3.372.769.4+3.3
- SWE-bench Multilingualtie56.956.5tie
AgentsMiniMax M2
- BrowseCompMiniMax M2 by 31.812.244+31.8
- GDPValMiniMax M2 by 16.99.726.6+16.9
ReasoningMiniMax M2
- Humanity's Last ExamMiniMax M2 by 310.713.7+3
- CritPttie0.30.9tie
- GPQA Diamondtie77.777.7tie
FactsClaude Sonnet 4
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 61.870.99.1+61.8
- AA-Omniscience · Accuracytie22.723.2tie
Following instructionsMiniMax M2
- IFBenchMiniMax M2 by 17.654.772.3+17.6
Other results18 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 by 46.70.2-46.5+46.7
- τ²-BenchMiniMax M2 by 41.845.287+41.8
- AA Agentic IndexMiniMax M2 by 29.917.647.5+29.9
- FinSearchComp-globalMiniMax M2 by 23.54265.5+23.5
- τ²-Bench Telecom (AA run)MiniMax M2 by 22.264.686.8+22.2
- BrowseComp-ZHMiniMax M2 by 19.429.148.5+19.4
- LiveCodeBenchMiniMax M2 by 14.568.583+14.5
- HLE (with tools)MiniMax M2 by 11.520.331.8+11.5
- Terminal-BenchMiniMax M2 by 10.835.546.3+10.8
- ArtifactsBenchMiniMax M2 by 9.557.366.8+9.5
- Artificial Analysis Coding IndexClaude Sonnet 4 by 8.437.629.2+8.4
- AIME 2025MiniMax M2 by 7.570.578+7.5
- GAIA (text only)MiniMax M2 by 7.468.375.7+7.4
- xbench-DeepSearchMiniMax M2 by 7.464.672+7.4
- MMLU-ProClaude Sonnet 4 by 1.783.782+1.7
- theagentcompanyClaude Sonnet 4 by 13736+1
- Multi-SWE-Benchtie35.736.2tie
- AA Intelligencetie18.918.6tie
Questions people ask
Which is better, Claude Sonnet 4 or MiniMax M2?
Claude Sonnet 4 and MiniMax M2 each win three of the six areas where both have results. Claude Sonnet 4 wins coding, facts and long documents; MiniMax M2 wins agents, reasoning and following instructions. MiniMax M2 costs 92% less.
Which is better for coding?
Claude Sonnet 4. It wins 3 of the 4 coding tests both models report; MiniMax M2 wins none, and 1 is a tie.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; MiniMax M2 costs $0.30 and $1.20. That makes MiniMax M2 about 92% cheaper for the same work.
How do you compare the two?
We use the 31 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 18 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.