Gemma 4 26B A4B vs MiMo V2 Pro
Wins 1 of 6 areas
Following instructions
Wins 5 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents
MiMo V2 Pro is the stronger all-rounder.Gemma 4 26B A4B is better at following instructions.
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.
- CodingWriting and fixing software05MiMo V2 Pro5 of 5 tests
- ReasoningHard problems that need careful thinking02MiMo V2 Pro2 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up02MiMo V2 Pro2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01MiMo V2 Pro1 of 1 test
- Long documentsFinding answers in very long texts01MiMo V2 Pro1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemma 4 26B A4B1 of 1 test
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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where MiMo V2 Pro pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+60.6points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+56.4points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+54.4points ahead
Where Gemma 4 26B A4B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+3.6points 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.
CodingMiMo V2 Pro
- SWE-bench VerifiedMiMo V2 Pro by 60.617.478+60.6
- SWE-bench MultilingualMiMo V2 Pro by 54.417.371.7+54.4
- Terminal-Bench HardMiMo V2 Pro by 27.313.640.9+27.3
- LMArena · WebDevMiMo V2 Pro by 74 rating points13591433+74 rating
- SciCodeMiMo V2 Pro by 2.54042.5+2.5
ReasoningMiMo V2 Pro
- Humanity's Last ExamMiMo V2 Pro by 11.119.330.4+11.1
- GPQA DiamondMiMo V2 Pro by 7.879.287+7.8
- CritPttie00.3tie
FactsMiMo V2 Pro
- AA-Omniscience · Non-hallucinationMiMo V2 Pro by 56.413.670+56.4
- AA-Omniscience · AccuracyMiMo V2 Pro by 7.519.126.6+7.5
Following instructionsGemma 4 26B A4B
- IFBenchGemma 4 26B A4B by 3.672.468.8+3.6
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-OmniscienceMiMo V2 Pro by 55.4-50.84.6+55.4
- AA Agentic IndexMiMo V2 Pro by 51.81162.8+51.8
- τ²-Bench Telecom (AA run)MiMo V2 Pro by 51.443.695+51.4
- Claw Eval (pass@3)MiMo V2 Pro by 33.52861.5+33.5
- Terminal-Bench 2.0MiMo V2 Pro by 22.934.257.1+22.9
- AA IntelligenceMiMo V2 Pro by 11.916.728.6+11.9
- PinchBenchMiMo V2 Pro by 6.374.781+6.3
- Artificial Analysis Coding IndexMiMo V2 Pro by 2.139.341.4+2.1
Questions people ask
Which is better, Gemma 4 26B A4B or MiMo V2 Pro?
MiMo V2 Pro wins five of the six areas where both have results: coding, agents, reasoning, facts and long documents. Gemma 4 26B A4B wins following instructions.
Which is better for coding?
MiMo V2 Pro. It wins 5 of the 5 coding tests both models report; Gemma 4 26B A4B wins none.
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.