DeepSeek-V3 is the stronger all-rounder.
Scores updated · 10 tests both models report · How we compare
Where each one wins
Tests won in each of the two 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.
Reasoning 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 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+38points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+24.6points ahead
Where LFM2-350M pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Following instructionsDeepSeek-V3
- IFBenchDeepSeek-V3 by 24.64116.4+24.6
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.
- GSM8KDeepSeek-V3 by 63.99430.1+63.9
- τ²-Bench (Retail)DeepSeek-V3 by 63.569.15.6+63.5
- MMLU-ProDeepSeek-V3 by 56.675.919.3+56.6
- MGSMDeepSeek-V3 by 50.379.829.5+50.3
- MMLUDeepSeek-V3 by 45.188.543.4+45.1
- MMMLUDeepSeek-V3 by 41.479.438+41.4
- τ²-BenchDeepSeek-V3 by 21.732.510.8+21.7
- IFEvalDeepSeek-V3 by 2186.165.1+21
Questions people ask
Which is better, DeepSeek-V3 or LFM2-350M?
DeepSeek-V3 wins all two areas where both have results: reasoning and following instructions. LFM2-350M wins none.
How do you compare the two?
We use the 10 benchmark tests both models have published scores on. The verdict counts the 2 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.