GPT-4o vs LFM2-2.6B
Wins 4 of 6 areas
Coding · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
GPT-4o is the stronger all-rounder.
Scores updated · 22 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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.
- CodingWriting and fixing software30GPT-4o3 of 3 tests
- FactsGetting facts right instead of making them up20GPT-4o2 of 2 tests
- Long documentsFinding answers in very long texts10GPT-4o1 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-4o1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
Agents, 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 GPT-4o pulls ahead
- Code for real scientific research problemsSciCode+30.8points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+25points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+22points ahead
Where LFM2-2.6B pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+3.7points ahead
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-4o
- SciCodeGPT-4o by 30.833.32.5+30.8
- LiveCodeBench v6GPT-4o by 16.530.914.4+16.5
- Terminal-Bench HardGPT-4o by 7.58.30.8+7.5
ReasoningEven
- GPQA DiamondGPT-4o by 2252.630.6+22
- Humanity's Last ExamLFM2-2.6B by 3.71.85.5+3.7
- CritPttie00tie
FactsGPT-4o
- AA-Omniscience · Non-hallucinationGPT-4o by 2562.137.1+25
- AA-Omniscience · AccuracyGPT-4o by 18.323.75.4+18.3
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.
- MMLU-ProGPT-4o by 48.774.726+48.7
- AA-OmniscienceGPT-4o by 43.6-10.5-54.1+43.6
- MMMLUGPT-4o by 2681.455.4+26
- MGSMGPT-4o by 16.290.574.3+16.2
- τ²-Bench Telecom (AA run)GPT-4o by 15.428.913.5+15.4
- MATH-500 (EM)GPT-4o by 1174.663.6+11
- MMLUGPT-4o by 9.473.864.4+9.4
- GSM8KGPT-4o by 8.590.982.4+8.5
- AA Agentic IndexGPT-4o by 3.98.44.5+3.9
- AA IntelligenceGPT-4o by 2.17.35.2+2.1
- IFEvalGPT-4o by 1.48179.6+1.4
Questions people ask
Which is better, GPT-4o or LFM2-2.6B?
GPT-4o wins four of the six areas where both have results: coding, facts, long documents and following instructions. LFM2-2.6B wins none. They are level on agents and reasoning.
Which is better for coding?
GPT-4o. It wins 3 of the 3 coding tests both models report; LFM2-2.6B wins none.
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. The verdict counts the 11 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.