Gemini 2.5 Pro vs Kimi K2 Instruct
Wins 5 of 6 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Wins 1 of 6 areas
Agents
Gemini 2.5 Pro is the stronger all-rounder.Kimi K2 Instruct is cheaper and better at agents.
Scores updated · 45 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.
- ReasoningHard problems that need careful thinking30Gemini 2.5 Pro3 of 3 tests
- CodingWriting and fixing software21Gemini 2.5 Pro2 of 3 tests
- FactsGetting facts right instead of making them up21Gemini 2.5 Pro2 of 3 tests
- Following instructionsDoing exactly what it is asked10Gemini 2.5 Pro1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10Gemini 2.5 Pro1 of 1 test
- AgentsCarrying out multi-step tasks on its own02Kimi K2 Instruct2 of 2 tests
Long documents rests on a single test.
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 72% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Gemini 2.5 Pro pulls ahead
- Reasons across sets of long documentsAA-LCR+16points ahead
- Code for real scientific research problemsSciCode+15.6points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+13.7points ahead
Where Kimi K2 Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+21.2points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+4.2points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+2.6points ahead
Every test, side by side
All 45 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 2.5 Pro
- SciCodeGemini 2.5 Pro by 15.646.330.7+15.6
- Terminal-Bench HardGemini 2.5 Pro by 326.523.5+3
- SWE-bench VerifiedKimi K2 Instruct by 2.663.265.8+2.6
AgentsKimi K2 Instruct
- GDPValKimi K2 Instruct by 18.2018.2+18.2
- BrowseCompKimi K2 Instruct by 4.29.914.1+4.2
ReasoningGemini 2.5 Pro
- Humanity's Last ExamGemini 2.5 Pro by 11.6186.4+11.6
- GPQA DiamondGemini 2.5 Pro by 6.983.676.7+6.9
- CritPtGemini 2.5 Pro by 2.62.60+2.6
FactsGemini 2.5 Pro
- AA-Omniscience · Non-hallucinationKimi K2 Instruct by 21.29.130.3+21.2
- AA-Omniscience · AccuracyGemini 2.5 Pro by 13.73925.4+13.7
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Pro by 10.9717.9+10.9
Following instructionsGemini 2.5 Pro
- IFBenchGemini 2.5 Pro by 748.741.7+7
- Multi-Challengetie53.654.1tie
Other results31 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 IndexKimi K2 Instruct by 34.23.537.7+34.2
- AIME 2025Gemini 2.5 Pro by 33.58349.5+33.5
- HarmBenchKimi K2 Instruct by 3265.497.4+32
- HMMT 2025Gemini 2.5 Pro by 26.965.738.8+26.9
- AIME 2024Gemini 2.5 Pro by 22.49269.6+22.4
- Artificial Analysis Coding IndexGemini 2.5 Pro by 20.846.725.9+20.8
- LiveCodeBenchGemini 2.5 Pro by 20.574.253.7+20.5
- SimpleQAGemini 2.5 Pro by 19.850.831+19.8
- τ²-Bench Telecom (AA run)Kimi K2 Instruct by 19.354.173.4+19.3
- Aider-PolyglotGemini 2.5 Pro by 16.576.560+16.5
- FinSearchComp-globalGemini 2.5 Pro by 13.142.629.5+13.1
- τ²-BenchKimi K2 Instruct by 11.85465.8+11.8
- vectara_factual_consistencyGemini 2.5 Pro by 10.99382.1+10.9
- AA-OmniscienceGemini 2.5 Pro by 10.3-16.4-26.6+10.3
- theagentcompanyGemini 2.5 Pro by 9.339.330+9.3
- xbench-DeepSearchKimi K2 Instruct by 55661+5
- MMLU-ProGemini 2.5 Pro by 4.98681.1+4.9
- vectara_avg_summary_lengthGemini 2.5 Pro by 47.2 rating points106.459.2+47.2 rating
- Terminal-BenchKimi K2 Instruct by 4.725.330+4.7
- ArtifactsBenchGemini 2.5 Pro by 3.557.754.2+3.5
- BrowseComp-ZHGemini 2.5 Pro by 3.432.228.8+3.4
- simple_safety_testsKimi K2 Instruct by 397100+3
- ZebraLogicGemini 2.5 Pro by 2.691.689+2.6
- HLE (with tools)Gemini 2.5 Pro by 1.528.426.9+1.5
- MATH-500 (EM)Gemini 2.5 Pro by 1.498.897.4+1.4
- AIR-Bench 2024tie73.674.1tie
- vectara_answer_ratetie99.198.6tie
- XSTesttie98.798.2tie
- AA Intelligencetie1515.3tie
- anthropic_red_teamtie99.599.3tie
- GAIA (text only)tie60.260.2tie
Questions people ask
Which is better, Gemini 2.5 Pro or Kimi K2 Instruct?
Gemini 2.5 Pro wins five of the six areas where both have results: coding, reasoning, facts, long documents and following instructions. Kimi K2 Instruct wins agents, and costs 72% less.
Which is better for coding?
Gemini 2.5 Pro. It wins 2 of the 3 coding tests both models report; Kimi K2 Instruct wins 1.
Which is cheaper?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; Kimi K2 Instruct costs $0.60 and $2.50. That makes Kimi K2 Instruct about 72% cheaper for the same work.
How do you compare the two?
We use the 45 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 31 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.