Gemma 4 31B vs MiMo V2 Omni
Wins 4 of 7 areas
Coding · Reasoning · Images and charts · Following instructions
Wins 3 of 7 areas
Agents · Facts · Long documents
Gemma 4 31B wins more areas, narrowly.MiMo V2 Omni is better at facts.
Scores updated · 19 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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 thinking20Gemma 4 31B2 of 3 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video20Gemma 4 31B2 of 2 tests
- CodingWriting and fixing software21Gemma 4 31B2 of 3 tests
- Following instructionsDoing exactly what it is asked10Gemma 4 31B1 of 1 test
- FactsGetting facts right instead of making them up01MiMo V2 Omni1 of 2 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own01MiMo V2 Omni1 of 1 test
- Long documentsFinding answers in very long texts01MiMo V2 Omni1 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.
Gemma 4 31B costs 76% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Gemma 4 31B pulls ahead
Where MiMo V2 Omni pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+36.1points ahead
- Real work tasks from 44 professionsGDPVal+34.8points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+22.8points ahead
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemma 4 31B
- SWE-bench VerifiedMiMo V2 Omni by 22.85274.8+22.8
- SciCodeGemma 4 31B by 8.845.536.7+8.8
- Terminal-Bench HardGemma 4 31B by 1.636.434.8+1.6
ReasoningGemma 4 31B
- GPQA DiamondGemma 4 31B by 2.985.782.8+2.9
- Humanity's Last ExamGemma 4 31B by 1.523.622.1+1.5
- CritPttie1.41.1tie
FactsMiMo V2 Omni
- AA-Omniscience · Non-hallucinationMiMo V2 Omni by 36.11551.1+36.1
- AA-Omniscience · Accuracytie2019.3tie
Images and chartsGemma 4 31B
- LMArena · VisionGemma 4 31B by 49 rating points12771228+49 rating
- MMMU-ProGemma 4 31B by 3.573.469.9+3.5
Following instructionsGemma 4 31B
- IFBenchGemma 4 31B by 22.175.653.5+22.1
Other results6 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 Agentic IndexMiMo V2 Omni by 51.96.758.6+51.9
- τ²-Bench Telecom (AA run)MiMo V2 Omni by 31.359.991.2+31.3
- Claw Eval (pass@3)MiMo V2 Omni by 29.82554.8+29.8
- AA-OmniscienceMiMo V2 Omni by 27.8-47.9-20.1+27.8
- AA IntelligenceMiMo V2 Omni by 9.214.723.9+9.2
- Artificial Analysis Coding IndexGemma 4 31B by 7.943.435.5+7.9
Questions people ask
Which is better, Gemma 4 31B or MiMo V2 Omni?
Gemma 4 31B wins four of the seven areas where both have results: coding, reasoning, images and charts and following instructions. MiMo V2 Omni wins agents, facts and long documents.
Which is better for coding?
Gemma 4 31B. It wins 2 of the 3 coding tests both models report; MiMo V2 Omni wins 1.
Which is cheaper?
Gemma 4 31B costs $0.17 per million input tokens and $0.40 per million output tokens; MiMo V2 Omni costs $0.40 and $2.00. That makes Gemma 4 31B about 76% cheaper for the same work.
How do you compare the two?
We use the 19 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 6 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.