DeepSeek-V4.1-Flash vs GPT-6.1 Sol
Wins 1 of 8 areas
Long documents
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Following instructions
GPT-6.1 Sol is the stronger all-rounder.DeepSeek-V4.1-Flash is cheaper and better at long documents.
Scores updated · 32 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 thinking06GPT-6.1 Sol6 of 6 tests
- FactsGetting facts right instead of making them up03GPT-6.1 Sol3 of 3 tests
- MathCompetition and research-level math03GPT-6.1 Sol3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02GPT-6.1 Sol2 of 2 tests
- CodingWriting and fixing software12GPT-6.1 Sol2 of 4 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own01GPT-6.1 Sol1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked01GPT-6.1 Sol1 of 1 test
- Long documentsFinding answers in very long texts10DeepSeek-V4.1-Flash1 of 1 test
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.
DeepSeek-V4.1-Flash costs 67% 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-6.1 Sol pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+53.7points ahead
- Solves new puzzle games it has never seenARC-AGI-3+52.5points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+42.2points ahead
Where DeepSeek-V4.1-Flash pulls ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+22.7points ahead
- Reasons across sets of long documentsAA-LCR+1points ahead
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-6.1 Sol
- LiveBench · Agentic CodingDeepSeek-V4.1-Flash by 22.777.354.5+22.7
- LMArena · WebDevGPT-6.1 Sol by 132 rating points16191751+132 rating
- SciCodeGPT-6.1 Sol by 2.351.954.2+2.3
- LiveBench · Codingtie8080.4tie
AgentsGPT-6.1 Sol
- Terminal-Bench 4.0GPT-6.1 Sol by 29.326.856.1+29.3
- GDPValtie5554.7tie
ReasoningGPT-6.1 Sol
- ARC-AGI-3GPT-6.1 Sol by 52.50.252.7+52.5
- CritPtGPT-6.1 Sol by 17.414.331.7+17.4
- SimpleBenchGPT-6.1 Sol by 16.266.782.9+16.2
- ARC-AGI-2GPT-6.1 Sol by 16.178.194.2+16.1
- Humanity's Last ExamGPT-6.1 Sol by 13.739.252.9+13.7
- LiveBench · ReasoningGPT-6.1 Sol by 5.986.792.6+5.9
FactsGPT-6.1 Sol
- AA-Omniscience · Non-hallucinationGPT-6.1 Sol by 42.23.545.7+42.2
- SimpleQA VerifiedGPT-6.1 Sol by 3142.973.9+31
- AA-Omniscience · AccuracyGPT-6.1 Sol by 15.746.462.1+15.7
Images and chartsGPT-6.1 Sol
- MMMU-ProGPT-6.1 Sol by 97786+9
- LMArena · VisionGPT-6.1 Sol by 10 rating points12781288+10 rating
MathGPT-6.1 Sol
- FrontierMath Tier 4GPT-6.1 Sol by 53.746.3100+53.7
- FrontierMath Tiers 1-3 (v2)GPT-6.1 Sol by 22.571.293.7+22.5
- LiveBench · MathematicsGPT-6.1 Sol by 3.593.396.8+3.5
Following instructionsGPT-6.1 Sol
- LiveBench · Instruction FollowingGPT-6.1 Sol by 4.27074.2+4.2
Other results10 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-OmniscienceGPT-6.1 Sol by 46.8-5.341.5+46.8
- Terminal-Bench-Science 0.1GPT-6.1 Sol by 41.315.757+41.3
- Terminal-Bench 4.0GPT-6.1 Sol by 2731.258.2+27
- OSWorld 2.0GPT-6.1 Sol by 17.154.371.4+17.1
- GDP (Surge AI)GPT-6.1 Sol by 14.817.232+14.8
- AA IntelligenceGPT-6.1 Sol by 12.339.551.8+12.3
- livebench_languageGPT-6.1 Sol by 8.981.290.1+8.9
- livebench_data_analysisGPT-6.1 Sol by 3.479.382.7+3.4
- ARC-AGI-1GPT-6.1 Sol by 393.596.5+3
- DeepSWE 1.1GPT-6.1 Sol by 174.275.2+1
Questions people ask
Which is better, DeepSeek-V4.1-Flash or GPT-6.1 Sol?
GPT-6.1 Sol wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and following instructions. DeepSeek-V4.1-Flash wins long documents, and costs 67% less.
Which is better for coding?
GPT-6.1 Sol. It wins 2 of the 4 coding tests both models report; DeepSeek-V4.1-Flash wins 1, and 1 is a tie.
Which is cheaper?
DeepSeek-V4.1-Flash costs $0.30 per million input tokens and $1.20 per million output tokens; GPT-6.1 Sol costs $2.00 and $2.50. That makes DeepSeek-V4.1-Flash about 67% cheaper for the same work.
How do you compare the two?
We use the 32 benchmark tests both models have published scores on. The verdict counts the 22 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.