DeepSeek-R1 0528-Qwen3-8B vs DeepSeek-V3.1
Wins 0 of 5 areas
—
Wins 5 of 5 areas
Coding · Reasoning · Facts · Long documents · Following instructions
DeepSeek-V3.1 is the stronger all-rounder.
Scores updated · 17 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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 thinking03DeepSeek-V3.13 of 3 tests
- CodingWriting and fixing software02DeepSeek-V3.12 of 2 tests
- FactsGetting facts right instead of making them up02DeepSeek-V3.12 of 2 tests
- Long documentsFinding answers in very long texts01DeepSeek-V3.11 of 1 test
- Following instructionsDoing exactly what it is asked01DeepSeek-V3.11 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where DeepSeek-V3.1 pulls ahead
- Reasons across sets of long documentsAA-LCR+41.7points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+23.5points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+21.6points ahead
Where DeepSeek-R1 0528-Qwen3-8B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 17 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3.1
- Terminal-Bench HardDeepSeek-V3.1 by 23.51.525+23.5
- SciCodeDeepSeek-V3.1 by 18.720.439.1+18.7
ReasoningDeepSeek-V3.1
- GPQA DiamondDeepSeek-V3.1 by 16.761.277.9+16.7
- Humanity's Last ExamDeepSeek-V3.1 by 8.45.914.3+8.4
- CritPtDeepSeek-V3.1 by 202+2
FactsDeepSeek-V3.1
- AA-Omniscience · AccuracyDeepSeek-V3.1 by 16.812.229+16.8
- AA-Omniscience · Non-hallucinationDeepSeek-V3.1 by 3.913.617.5+3.9
Following instructionsDeepSeek-V3.1
- IFBenchDeepSeek-V3.1 by 21.619.941.5+21.6
Other results8 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.
- τ²-Bench Telecom (AA run)DeepSeek-V3.1 by 37.4037.4+37.4
- AA-OmniscienceDeepSeek-V3.1 by 34-63.6-29.6+34
- AIME 2025DeepSeek-R1 0528-Qwen3-8B by 26.576.349.8+26.5
- HMMT Feb. 2025DeepSeek-V3.1 by 24.361.585.8+24.3
- Artificial Analysis Coding IndexDeepSeek-V3.1 by 21.97.829.7+21.9
- AIME 2024DeepSeek-V3.1 by 7.18693.1+7.1
- AA IntelligenceDeepSeek-V3.1 by 5.48.113.5+5.4
- LiveCodeBenchDeepSeek-R1 0528-Qwen3-8B by 4.160.556.4+4.1
Questions people ask
Which is better, DeepSeek-R1 0528-Qwen3-8B or DeepSeek-V3.1?
DeepSeek-V3.1 wins all five areas where both have results: coding, reasoning, facts, long documents and following instructions. DeepSeek-R1 0528-Qwen3-8B wins none.
Which is better for coding?
DeepSeek-V3.1. It wins 2 of the 2 coding tests both models report; DeepSeek-R1 0528-Qwen3-8B wins none.
How do you compare the two?
We use the 17 benchmark tests both models have published scores on. The verdict counts the 9 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.