GPT-5.2 vs Kimi K2 Instruct
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.Kimi K2 Instruct is cheaper.
Scores updated · 34 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 software50GPT-5.25 of 5 tests
- ReasoningHard problems that need careful thinking30GPT-5.23 of 3 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.
Kimi K2 Instruct costs 80% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where GPT-5.2 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+51.7points ahead
- Olympiad math problems with short answersIMOAnswerBench+40.5points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+33.7points ahead
Where Kimi K2 Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+11.5points ahead
Every test, side by side
All 34 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 23.54723.5+23.5
- SciCodeGPT-5.2 by 21.452.130.7+21.4
- SWE-bench MultilingualGPT-5.2 by 19.466.747.3+19.4
- SWE-bench VerifiedGPT-5.2 by 14.28065.8+14.2
- SWE-bench ProGPT-5.2 by 2.229.927.7+2.2
AgentsGPT-5.2
- BrowseCompGPT-5.2 by 51.765.814.1+51.7
- GDPValGPT-5.2 by 30.148.318.2+30.1
ReasoningGPT-5.2
- Humanity's Last ExamGPT-5.2 by 31.337.76.4+31.3
- GPQA DiamondGPT-5.2 by 13.690.376.7+13.6
- CritPtGPT-5.2 by 11.611.60+11.6
FactsGPT-5.2
- AA-Omniscience · AccuracyGPT-5.2 by 18.944.325.4+18.9
- AA-Omniscience · Non-hallucinationKimi K2 Instruct by 11.518.830.3+11.5
- Vectara HHEM hallucination ratelower is betterGPT-5.2 by 7.110.817.9+7.1
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.
- HMMT 2025GPT-5.2 by 60.699.438.8+60.6
- AIME 2025GPT-5.2 by 50.510049.5+50.5
- AIME25 no toolsGPT-5.2 by 479851+47
- LiveCodeBenchGPT-5.2 by 35.38953.7+35.3
- AA-OmniscienceGPT-5.2 by 25.7-0.9-26.6+25.7
- Artificial Analysis Coding IndexGPT-5.2 by 22.848.725.9+22.8
- AA Agentic IndexGPT-5.2 by 22.560.237.7+22.5
- τ²-BenchGPT-5.2 by 19.785.565.8+19.7
- HLE (with tools)GPT-5.2 by 18.645.526.9+18.6
- GPQA (unspecified)GPT-5.2 by 18.292.474.2+18.2
- AA IntelligenceGPT-5.2 by 15.130.415.3+15.1
- vectara_avg_summary_lengthGPT-5.2 by 127.1 rating points186.359.2+127.1 rating
- τ²-Bench (Retail)GPT-5.2 by 11.48270.6+11.4
- τ²-Bench Telecom (AA run)GPT-5.2 by 11.484.873.4+11.4
- vectara_factual_consistencyGPT-5.2 by 7.189.282.1+7.1
- MMLU-ProGPT-5.2 by 5.686.781.1+5.6
- LiveBenchKimi K2 Instruct by 1.674.876.4+1.6
- vectara_answer_rateGPT-5.2 by 1.410098.6+1.4
Questions people ask
Which is better, GPT-5.2 or Kimi K2 Instruct?
GPT-5.2 wins all seven areas where both have results: coding, agents, reasoning, facts, math, long documents and following instructions. Kimi K2 Instruct wins none, but costs 80% less.
Which is better for coding?
GPT-5.2. It wins 5 of the 5 coding tests both models report; Kimi K2 Instruct wins none.
Which is cheaper?
GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens; Kimi K2 Instruct costs $0.60 and $2.50. That makes Kimi K2 Instruct about 80% cheaper for the same work.
How do you compare the two?
We use the 34 benchmark tests both models have published scores on. The verdict counts the 16 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.