GPT-6.1 Sol vs Kimi K3
Wins 6 of 8 areas
Agents · Reasoning · Facts · Images and charts · Math · Following instructions
Wins 2 of 8 areas
Coding · Long documents
GPT-6.1 Sol is the stronger all-rounder.Kimi K3 is better at coding.
Scores updated · 30 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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 thinking50GPT-6.1 Sol5 of 5 tests
- AgentsCarrying out multi-step tasks on its own30GPT-6.1 Sol3 of 3 tests
- MathCompetition and research-level math30GPT-6.1 Sol3 of 3 tests
- FactsGetting facts right instead of making them up21GPT-6.1 Sol2 of 3 tests
- Images and chartsUnderstanding pictures, charts and video10GPT-6.1 Sol1 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-6.1 Sol1 of 1 test
- CodingWriting and fixing software13Kimi K33 of 4 tests
- Long documentsFinding answers in very long texts01Kimi K31 of 1 test
Images and charts, 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.
GPT-6.1 Sol costs 75% 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-6.1 Sol pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+61points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+43.5points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+33.8points ahead
Where Kimi K3 pulls ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+7.6points ahead
- Reasons across sets of long documentsAA-LCR+5.7points ahead
- Code for real scientific research problemsSciCode+5.3points ahead
Every test, side by side
All 30 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi K3
- LMArena · WebDevGPT-6.1 Sol by 94 rating points17491655+94 rating
- LiveBench · Agentic CodingKimi K3 by 7.654.562.2+7.6
- SciCodeKimi K3 by 5.354.259.5+5.3
- LiveBench · CodingKimi K3 by 1.180.481.5+1.1
AgentsGPT-6.1 Sol
- Terminal-Bench 4.0GPT-6.1 Sol by 43.556.112.6+43.5
- AA ApexAgentsGPT-6.1 Sol by 18.76041.3+18.7
- GDPValGPT-6.1 Sol by 354.751.7+3
ReasoningGPT-6.1 Sol
- ARC-AGI-2GPT-6.1 Sol by 33.894.260.4+33.8
- SimpleBenchGPT-6.1 Sol by 22.282.960.7+22.2
- CritPtGPT-6.1 Sol by 8.331.723.4+8.3
- Humanity's Last ExamGPT-6.1 Sol by 652.946.9+6
- LiveBench · ReasoningGPT-6.1 Sol by 1.992.690.7+1.9
FactsGPT-6.1 Sol
- SimpleQA VerifiedGPT-6.1 Sol by 23.373.950.6+23.3
- AA-Omniscience · AccuracyGPT-6.1 Sol by 14.562.147.6+14.5
- AA-Omniscience · Non-hallucinationKimi K3 by 1.145.746.8+1.1
MathGPT-6.1 Sol
- FrontierMath Tier 4GPT-6.1 Sol by 6110039+61
- FrontierMath Tiers 1-3 (v2)GPT-6.1 Sol by 21.593.772.2+21.5
- LiveBench · MathematicsGPT-6.1 Sol by 12.496.884.4+12.4
Following instructionsGPT-6.1 Sol
- LiveBench · Instruction FollowingGPT-6.1 Sol by 2.874.271.4+2.8
Other results9 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.
- Terminal-Bench 4.0GPT-6.1 Sol by 45.658.212.6+45.6
- AA-OmniscienceGPT-6.1 Sol by 21.841.519.7+21.8
- HiL-Bench (Tools-allowed)GPT-6.1 Sol by 19.662.342.7+19.6
- OSWorld 2.0GPT-6.1 Sol by 13.171.458.3+13.1
- AA IntelligenceGPT-6.1 Sol by 8.251.843.6+8.2
- DeepSWE 1.1GPT-6.1 Sol by 6.275.269+6.2
- livebench_languageGPT-6.1 Sol by 4.690.185.5+4.6
- livebench_data_analysisGPT-6.1 Sol by 482.778.7+4
- ARC-AGI-1GPT-6.1 Sol by 296.594.5+2
Questions people ask
Which is better, GPT-6.1 Sol or Kimi K3?
GPT-6.1 Sol wins six of the eight areas we test: agents, reasoning, facts, images and charts, math and following instructions. Kimi K3 wins coding and long documents.
Which is better for coding?
Kimi K3. It wins 3 of the 4 coding tests both models report; GPT-6.1 Sol wins 1.
Which is cheaper?
GPT-6.1 Sol costs $2.00 per million input tokens and $2.50 per million output tokens; Kimi K3 costs $3.00 and $15.00. That makes GPT-6.1 Sol about 75% cheaper for the same work.
How do you compare the two?
We use the 30 benchmark tests both models have published scores on. The verdict counts the 21 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.