GLM-4.7 vs MiMo V2 Flash
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Math · Following instructions
Wins 0 of 7 areas
—
GLM-4.7 is the stronger all-rounder.MiMo V2 Flash is cheaper.
Scores updated · 36 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.
- CodingWriting and fixing software42GLM-4.74 of 7 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own21GLM-4.72 of 3 tests
- ReasoningHard problems that need careful thinking21GLM-4.72 of 3 tests
- FactsGetting facts right instead of making them up10GLM-4.71 of 2 tests · 1 tie
- MathCompetition and research-level math10GLM-4.71 of 1 test
- Following instructionsDoing exactly what it is asked10GLM-4.71 of 1 test
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Math, 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.
MiMo V2 Flash costs 86% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where GLM-4.7 pulls ahead
- Real work tasks from 44 professionsGDPVal+19.2points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+9.1points ahead
- Code for real scientific research problemsSciCode+5.7points ahead
Where MiMo V2 Flash pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+16.5points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+6.3points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+5points ahead
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGLM-4.7
- Terminal-Bench 2.1MiMo V2 Flash by 16.545.361.8+16.5
- LMArena · WebDevGLM-4.7 by 104 rating points14351331+104 rating
- SciCodeGLM-4.7 by 5.745.139.4+5.7
- SWE-bench MultilingualMiMo V2 Flash by 566.771.7+5
- LiveCodeBench v6GLM-4.7 by 4.384.980.6+4.3
- Terminal-Bench HardGLM-4.7 by 3.831.828+3.8
- SWE-bench Verifiedtie73.873.4tie
AgentsGLM-4.7
- GDPValGLM-4.7 by 19.225.86.6+19.2
- τ-Bench V3 · BankingGLM-4.7 by 9.112.23.1+9.1
- BrowseCompMiMo V2 Flash by 6.35258.3+6.3
ReasoningGLM-4.7
- Humanity's Last ExamGLM-4.7 by 4.627.422.8+4.6
- CritPtMiMo V2 Flash by 2.61.74.3+2.6
- GPQA DiamondGLM-4.7 by 1.385.984.6+1.3
FactsGLM-4.7
- AA-Omniscience · AccuracyGLM-4.7 by 4.529.324.8+4.5
- AA-Omniscience · Non-hallucinationtie76.6tie
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.
- GAIA (no file)MiMo V2 Flash by 16.361.978.2+16.3
- BrowseComp-ZHGLM-4.7 by 15.466.651.2+15.4
- AA Agentic IndexGLM-4.7 by 14.226.212+14.2
- HMMT Feb. 2025GLM-4.7 by 12.797.184.4+12.7
- browsecomp_with_context_managerGLM-4.7 by 9.267.558.3+9.2
- AA-OmniscienceGLM-4.7 by 8.9-36.4-45.4+8.9
- xbench-DeepSearchGLM-4.7 by 8.352.344+8.3
- xbench-DeepSearch (2025.10)GLM-4.7 by 8.352.344+8.3
- ResearchRubricsGLM-4.7 by 7.76254.3+7.7
- τ²-BenchGLM-4.7 by 7.187.480.3+7.1
- Artificial Analysis Coding IndexMiMo V2 Flash by 4.545.349.8+4.5
- Terminal-BenchGLM-4.7 by 2.833.330.5+2.8
- HMMT Nov. 2025GLM-4.7 by 2.593.591+2.5
- Terminal-Bench 2.0GLM-4.7 by 2.54138.5+2.5
- AIME 2025GLM-4.7 by 1.695.794.1+1.6
- AA IntelligenceGLM-4.7 by 1.422.220.8+1.4
- τ²-Bench Telecom (AA run)tie95.995tie
- MMLU-Protie84.384.9tie
Questions people ask
Which is better, GLM-4.7 or MiMo V2 Flash?
GLM-4.7 wins six of the seven areas where both have results: coding, agents, reasoning, facts, math and following instructions. MiMo V2 Flash wins none, but costs 86% less. They are level on long documents.
Which is better for coding?
GLM-4.7. It wins 4 of the 7 coding tests both models report; MiMo V2 Flash wins 2, and 1 is a tie.
Which is cheaper?
GLM-4.7 costs $0.60 per million input tokens and $2.20 per million output tokens; MiMo V2 Flash costs $0.10 and $0.30. That makes MiMo V2 Flash about 86% cheaper for the same work.
How do you compare the two?
We use the 36 benchmark tests both models have published scores on. The verdict counts the 18 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.