Gemini 3.1 Pro vs Kimi K2.7 Code
Wins 6 of 7 areas
Coding · Reasoning · Facts · Math · Long documents · Following instructions
Wins 0 of 7 areas
—
Gemini 3.1 Pro is the stronger all-rounder.Kimi K2.7 Code is cheaper.
Scores updated · 35 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 thinking50Gemini 3.1 Pro5 of 5 tests
- FactsGetting facts right instead of making them up30Gemini 3.1 Pro3 of 3 tests
- MathCompetition and research-level math30Gemini 3.1 Pro3 of 3 tests
- CodingWriting and fixing software42Gemini 3.1 Pro4 of 6 tests
- Following instructionsDoing exactly what it is asked20Gemini 3.1 Pro2 of 2 tests
- Long documentsFinding answers in very long texts10Gemini 3.1 Pro1 of 1 test
- AgentsCarrying out multi-step tasks on its own22Even2 each
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 K2.7 Code costs 65% 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 3.1 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+37points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+31.5points ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+22.8points ahead
Where Kimi K2.7 Code pulls ahead
- Real work tasks from 44 professionsGDPVal+12.3points ahead
- Multi-step tasks using many real software toolsMCP Atlas+6.8points ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+1.6points ahead
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3.1 Pro
- SciCodeGemini 3.1 Pro by 10.958.747.8+10.9
- Terminal-Bench HardGemini 3.1 Pro by 9.153.844.7+9.1
- Terminal-Bench 2.1Gemini 3.1 Pro by 6.473.867.4+6.4
- LMArena · WebDevKimi K2.7 Code by 26 rating points14471473+26 rating
- LiveBench · CodingGemini 3.1 Pro by 2.576.574+2.5
- LiveBench · Agentic CodingKimi K2.7 Code by 1.644.145.7+1.6
AgentsEven
- GDPValKimi K2.7 Code by 12.314.727+12.3
- MCP AtlasKimi K2.7 Code by 6.869.276+6.8
- Terminal-Bench 4.0Gemini 3.1 Pro by 341+3
- τ-Bench V3 · BankingGemini 3.1 Pro by 1.221.420.2+1.2
ReasoningGemini 3.1 Pro
- SimpleBenchGemini 3.1 Pro by 21.779.657.9+21.7
- Humanity's Last ExamGemini 3.1 Pro by 124735+12
- CritPtGemini 3.1 Pro by 7.717.710+7.7
- GPQA DiamondGemini 3.1 Pro by 4.594.189.6+4.5
- LiveBench · ReasoningGemini 3.1 Pro by 1.28482.8+1.2
FactsGemini 3.1 Pro
- SimpleQA VerifiedGemini 3.1 Pro by 3773.536.5+37
- AA-Omniscience · Non-hallucinationGemini 3.1 Pro by 31.549.117.6+31.5
- AA-Omniscience · AccuracyGemini 3.1 Pro by 15.354.939.6+15.3
MathGemini 3.1 Pro
- FrontierMath Tier 4Gemini 3.1 Pro by 14.626.812.2+14.6
- LiveBench · MathematicsGemini 3.1 Pro by 11.49179.6+11.4
- FrontierMath Tiers 1-3 (v2)Gemini 3.1 Pro by 5.759.654+5.7
Following instructionsGemini 3.1 Pro
- LiveBench · Instruction FollowingGemini 3.1 Pro by 22.879.156.3+22.8
- IFBenchGemini 3.1 Pro by 1477.163.1+14
Other results11 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-OmniscienceGemini 3.1 Pro by 42.131.9-10.2+42.1
- MCPMarkKimi K2.7 Code by 25.255.981.1+25.2
- DeepSWE 1.1Kimi K2.7 Code by 191231+19
- livebench_data_analysisGemini 3.1 Pro by 15.878.562.7+15.8
- Program BenchKimi K2.7 Code by 14.139.553.6+14.1
- AA Agentic IndexKimi K2.7 Code by 12.210.322.5+12.2
- Artificial Analysis Coding IndexGemini 3.1 Pro by 868.860.8+8
- LiveBenchGemini 3.1 Pro by 879.971.9+8
- livebench_languageGemini 3.1 Pro by 7.585.477.9+7.5
- τ²-Bench Telecom (AA run)Gemini 3.1 Pro by 5.595.690.1+5.5
- AA IntelligenceGemini 3.1 Pro by 3.929.725.8+3.9
Questions people ask
Which is better, Gemini 3.1 Pro or Kimi K2.7 Code?
Gemini 3.1 Pro wins six of the seven areas where both have results: coding, reasoning, facts, math, long documents and following instructions. Kimi K2.7 Code wins none, but costs 65% less. They are level on agents.
Which is better for coding?
Gemini 3.1 Pro. It wins 4 of the 6 coding tests both models report; Kimi K2.7 Code wins 2.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Kimi K2.7 Code costs $0.95 and $4.00. That makes Kimi K2.7 Code about 65% cheaper for the same work.
How do you compare the two?
We use the 35 benchmark tests both models have published scores on. The verdict counts the 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 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.