GPT-4o vs Seed Oss 36B Instruct
Wins 1 of 6 areas
Facts
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
Seed Oss 36B Instruct is the stronger all-rounder.GPT-4o is better at facts.
Scores updated · 27 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.
- ReasoningHard problems that need careful thinking02Seed Oss 36B Instruct2 of 3 tests · 1 tie
- CodingWriting and fixing software12Seed Oss 36B Instruct2 of 3 tests
- AgentsCarrying out multi-step tasks on its own01Seed Oss 36B Instruct1 of 1 test
- Long documentsFinding answers in very long texts01Seed Oss 36B Instruct1 of 1 test
- Following instructionsDoing exactly what it is asked01Seed Oss 36B Instruct1 of 1 test
- FactsGetting facts right instead of making them up20GPT-4o2 of 2 tests
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.
Seed Oss 36B Instruct costs 96% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Seed Oss 36B Instruct pulls ahead
- Recent programming contest problemsLiveCodeBench v6+36.5points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+20points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+8.1points ahead
Where GPT-4o pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+48.5points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+5.5points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+1.5points ahead
Every test, side by side
All 27 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingSeed Oss 36B Instruct
- LiveCodeBench v6Seed Oss 36B Instruct by 36.530.967.4+36.5
- SciCodeSeed Oss 36B Instruct by 3.233.336.5+3.2
- Terminal-Bench HardGPT-4o by 1.58.36.8+1.5
ReasoningSeed Oss 36B Instruct
- GPQA DiamondSeed Oss 36B Instruct by 2052.672.6+20
- Humanity's Last ExamSeed Oss 36B Instruct by 8.11.89.9+8.1
- CritPttie00tie
FactsGPT-4o
- AA-Omniscience · Non-hallucinationGPT-4o by 48.562.113.6+48.5
- AA-Omniscience · AccuracyGPT-4o by 5.523.718.2+5.5
Long documentsSeed Oss 36B Instruct
- AA-LCRSeed Oss 36B Instruct by 5.35661.3+5.3
Following instructionsSeed Oss 36B Instruct
- IFBenchSeed Oss 36B Instruct by 5.93641.9+5.9
Other results16 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.
- AIME 2024Seed Oss 36B Instruct by 82.49.391.7+82.4
- AIME 2025Seed Oss 36B Instruct by 7311.784.7+73
- AA-OmniscienceGPT-4o by 42-10.5-52.5+42
- SimpleQAGPT-4o by 28.538.29.7+28.5
- τ²-Bench Telecom (AA run)Seed Oss 36B Instruct by 20.528.949.4+20.5
- AA Agentic IndexSeed Oss 36B Instruct by 19.38.427.7+19.3
- MMLUSeed Oss 36B Instruct by 13.673.887.4+13.6
- SuperGPQASeed Oss 36B Instruct by 13.342.455.7+13.3
- AIR-Bench 2024Seed Oss 36B Instruct by 13.262.475.6+13.2
- TAU-bench (retail)Seed Oss 36B Instruct by 10.160.370.4+10.1
- MMLU-ProSeed Oss 36B Instruct by 874.782.7+8
- Artificial Analysis Coding IndexGPT-4o by 7.524.216.7+7.5
- AA IntelligenceSeed Oss 36B Instruct by 4.87.312.1+4.8
- IFEvalSeed Oss 36B Instruct by 4.88185.8+4.8
- TAU-bench (airline)Seed Oss 36B Instruct by 3.242.846+3.2
- MMMLUGPT-4o by 381.478.4+3
Questions people ask
Which is better, GPT-4o or Seed Oss 36B Instruct?
Seed Oss 36B Instruct wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. GPT-4o wins facts.
Which is better for coding?
Seed Oss 36B Instruct. It wins 2 of the 3 coding tests both models report; GPT-4o wins 1.
Which is cheaper?
GPT-4o costs $5.00 per million input tokens and $15.00 per million output tokens; Seed Oss 36B Instruct costs $0.21 and $0.57. That makes Seed Oss 36B Instruct about 96% cheaper for the same work.
How do you compare the two?
We use the 27 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 16 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.