Gemini 3.1 Pro vs Inkling
Wins 6 of 8 areas
Coding · Reasoning · Facts · Images and charts · Math · Long documents
Wins 1 of 8 areas
Agents
Gemini 3.1 Pro is the stronger all-rounder.Inkling is cheaper and better at agents.
Both rank among the ten best models we track in following instructions.
Scores updated · 46 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 thinking60Gemini 3.1 Pro6 of 6 tests
- MathCompetition and research-level math50Gemini 3.1 Pro5 of 5 tests
- CodingWriting and fixing software51Gemini 3.1 Pro5 of 6 tests
- FactsGetting facts right instead of making them up30Gemini 3.1 Pro3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20Gemini 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 own13Inkling3 of 4 tests
- Following instructionsDoing exactly what it is asked11Even1 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.
Inkling costs 64% 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
- Abstract visual puzzles that people can solveARC-AGI-2+40.6points ahead
- Common-sense trick questionsSimpleBench+29.6points ahead
- Short factual questions, answered correctlySimpleQA Verified+29.6points ahead
Where Inkling pulls ahead
- Real work tasks from 44 professionsGDPVal+14.2points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+7.7points ahead
- Multi-step tasks using many real software toolsMCP Atlas+6.8points ahead
Every test, side by side
All 46 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3.1 Pro
- Terminal-Bench 2.1Gemini 3.1 Pro by 18.773.855.1+18.7
- SciCodeGemini 3.1 Pro by 11.758.747+11.7
- LiveBench · CodingGemini 3.1 Pro by 5.576.571+5.5
- LiveBench · Agentic CodingInkling by 5.344.149.4+5.3
- LMArena · WebDevGemini 3.1 Pro by 32 rating points14471415+32 rating
- SWE-bench VerifiedGemini 3.1 Pro by 380.677.6+3
AgentsInkling
- GDPValInkling by 14.214.628.8+14.2
- τ-Bench V3 · BankingInkling by 7.721.429.1+7.7
- MCP AtlasInkling by 6.869.276+6.8
- Terminal-Bench 4.0Gemini 3.1 Pro by 341+3
ReasoningGemini 3.1 Pro
- ARC-AGI-2Gemini 3.1 Pro by 40.677.136.5+40.6
- SimpleBenchGemini 3.1 Pro by 29.679.650+29.6
- Humanity's Last ExamGemini 3.1 Pro by 15.14731.9+15.1
- CritPtGemini 3.1 Pro by 12.317.75.4+12.3
- GPQA DiamondGemini 3.1 Pro by 6.994.187.2+6.9
- LiveBench · ReasoningGemini 3.1 Pro by 5.68478.3+5.6
FactsGemini 3.1 Pro
- SimpleQA VerifiedGemini 3.1 Pro by 29.673.543.9+29.6
- AA-Omniscience · Non-hallucinationGemini 3.1 Pro by 16.849.132.3+16.8
- AA-Omniscience · AccuracyGemini 3.1 Pro by 13.354.941.5+13.3
Images and chartsGemini 3.1 Pro
- MMMU-ProGemini 3.1 Pro by 8.982.473.5+8.9
- CharXiv (RQ)Gemini 3.1 Pro by 5.283.378.1+5.2
MathGemini 3.1 Pro
- FrontierMath Tiers 1-3 (v2)Gemini 3.1 Pro by 26.459.633.3+26.4
- FrontierMath Tier 4Gemini 3.1 Pro by 21.926.84.9+21.9
- HMMT Feb. 2026Gemini 3.1 Pro by 8.494.786.3+8.4
- LiveBench · MathematicsGemini 3.1 Pro by 2.69188.4+2.6
- AIME 2026Gemini 3.1 Pro by 1.298.397.1+1.2
Following instructionsEven
- LiveBench · Instruction FollowingGemini 3.1 Pro by 979.170.1+9
- IFBenchInkling by 2.777.179.8+2.7
Other results17 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 29.931.92+29.9
- GDPval-AA v2Inkling by 276 rating points9621238+276 rating
- ARC-AGI-1Gemini 3.1 Pro by 18.59879.5+18.5
- Artificial Analysis Coding IndexGemini 3.1 Pro by 16.768.852.1+16.7
- AA Agentic IndexInkling by 1410.324.3+14
- livebench_languageGemini 3.1 Pro by 11.985.473.5+11.9
- BrowseComp (w/ Ctx)Gemini 3.1 Pro by 8.885.977.1+8.8
- charxiv_rq_with_pythonGemini 3.1 Pro by 7.989.982+7.9
- τ³-Bench BankingInkling by 7.216.523.7+7.2
- livebench_data_analysisGemini 3.1 Pro by 5.778.572.8+5.7
- HLE (with tools)Gemini 3.1 Pro by 5.451.446+5.4
- MMAUGemini 3.1 Pro by 5.382.577.2+5.3
- AA IntelligenceGemini 3.1 Pro by 4.729.725+4.7
- Global-MMLU-LiteGemini 3.1 Pro by 492.788.7+4
- VoiceBenchGemini 3.1 Pro by 2.994.391.4+2.9
- StrongREJECTtie9898.6tie
- SWEBench Pro Publictie54.254.3tie
Questions people ask
Which is better, Gemini 3.1 Pro or Inkling?
Gemini 3.1 Pro wins six of the eight areas we test: coding, reasoning, facts, images and charts, math and long documents. Inkling wins agents, and costs 64% less. They are level on following instructions.
Which is better for coding?
Gemini 3.1 Pro. It wins 5 of the 6 coding tests both models report; Inkling wins 1.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Inkling costs $1.00 and $4.05. That makes Inkling about 64% cheaper for the same work.
How do you compare the two?
We use the 46 benchmark tests both models have published scores on. The verdict counts the 29 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 17 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.