GPT-5.2 vs MiniMax M2.1
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Math · Long documents · Following instructions
Wins 0 of 7 areas
—
GPT-5.2 is the stronger all-rounder.MiniMax M2.1 is cheaper.
Scores updated · 38 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 thinking40GPT-5.24 of 4 tests
- CodingWriting and fixing software42GPT-5.24 of 6 tests
- AgentsCarrying out multi-step tasks on its own20GPT-5.22 of 2 tests
- FactsGetting facts right instead of making them up21GPT-5.22 of 3 tests
- MathCompetition and research-level math10GPT-5.21 of 1 test
- Long documentsFinding answers in very long texts10GPT-5.21 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-5.21 of 1 test
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.
MiniMax M2.1 costs 90% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where GPT-5.2 pulls ahead
- Olympiad math problems with short answersIMOAnswerBench+25.9points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+23.1points ahead
- Real work tasks from 44 professionsGDPVal+18.6points ahead
Where MiniMax M2.1 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+12.7points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+6.9points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+5.8points ahead
Every test, side by side
All 38 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.2
- Terminal-Bench HardGPT-5.2 by 18.24728.8+18.2
- SWE-bench VerifiedGPT-5.2 by 138067+13
- SciCodeGPT-5.2 by 11.452.140.7+11.4
- SWE-bench ProMiniMax M2.1 by 6.929.936.8+6.9
- SWE-bench MultilingualMiniMax M2.1 by 5.866.772.5+5.8
- LMArena · WebDevGPT-5.2 by 31 rating points14151384+31 rating
AgentsGPT-5.2
- GDPValGPT-5.2 by 18.648.329.7+18.6
- BrowseCompGPT-5.2 by 3.865.862+3.8
ReasoningGPT-5.2
- Humanity's Last ExamGPT-5.2 by 14.537.723.2+14.5
- CritPtGPT-5.2 by 11.311.60.3+11.3
- SimpleBenchGPT-5.2 by 11.145.834.7+11.1
- GPQA DiamondGPT-5.2 by 7.390.383+7.3
FactsGPT-5.2
- AA-Omniscience · AccuracyGPT-5.2 by 23.144.321.2+23.1
- AA-Omniscience · Non-hallucinationMiniMax M2.1 by 12.718.831.5+12.7
- Vectara HHEM hallucination ratelower is betterGPT-5.2 by 110.811.8+1
Other results20 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-OmniscienceGPT-5.2 by 32-0.9-32.9+32
- HMMT Feb. 2025GPT-5.2 by 2910071+29
- HMMT Nov. 2025GPT-5.2 by 21.595.874.3+21.5
- AIME 2025GPT-5.2 by 1910081+19
- Artificial Analysis Coding IndexGPT-5.2 by 15.948.732.8+15.9
- AIME25 no toolsGPT-5.2 by 159883+15
- AA Agentic IndexGPT-5.2 by 12.860.247.4+12.8
- SWT-benchGPT-5.2 by 11.480.769.3+11.4
- LiveCodeBenchGPT-5.2 by 118978+11
- AA IntelligenceGPT-5.2 by 9.530.420.9+9.5
- BrowseComp (context management)GPT-5.2 by 87062+8
- vectara_avg_summary_lengthGPT-5.2 by 79.4 rating points186.3106.9+79.4 rating
- Terminal-Bench 2.0GPT-5.2 by 6.15447.9+6.1
- ToolathlonGPT-5.2 by 2.846.343.5+2.8
- vectara_answer_rateGPT-5.2 by 1.510098.5+1.5
- τ²-BenchMiniMax M2.1 by 1.585.587+1.5
- MMLU-ProMiniMax M2.1 by 1.386.788+1.3
- vectara_factual_consistencyGPT-5.2 by 189.288.2+1
- τ²-Bench Telecom (AA run)tie84.885.4tie
- SWE-Perftie3.63.1tie
Questions people ask
Which is better, GPT-5.2 or MiniMax M2.1?
GPT-5.2 wins all seven areas where both have results: coding, agents, reasoning, facts, math, long documents and following instructions. MiniMax M2.1 wins none, but costs 90% less.
Which is better for coding?
GPT-5.2. It wins 4 of the 6 coding tests both models report; MiniMax M2.1 wins 2.
Which is cheaper?
GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens; MiniMax M2.1 costs $0.30 and $1.20. That makes MiniMax M2.1 about 90% cheaper for the same work.
How do you compare the two?
We use the 38 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 20 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.