Gemma 3 27B vs Llama 3.3 70B Instruct
Wins 0 of 6 areas
—
Wins 5 of 6 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Llama 3.3 70B Instruct is the stronger all-rounder.Gemma 3 27B is cheaper.
Scores updated · 28 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.
- FactsGetting facts right instead of making them up03Llama 3.3 70B Instruct3 of 3 tests
- CodingWriting and fixing software01Llama 3.3 70B Instruct1 of 3 tests · 2 ties
- ReasoningHard problems that need careful thinking01Llama 3.3 70B Instruct1 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts01Llama 3.3 70B Instruct1 of 1 test
- Following instructionsDoing exactly what it is asked01Llama 3.3 70B Instruct1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 2 ties
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.
Gemma 3 27B costs 83% 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 Llama 3.3 70B Instruct pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+15.3points ahead
- Reasons across sets of long documentsAA-LCR+8.4points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+7points ahead
Where Gemma 3 27B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 28 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingLlama 3.3 70B Instruct
- SciCodeLlama 3.3 70B Instruct by 2.723.326+2.7
- Terminal-Bench Hardtie3.83tie
- Terminal-Bench 2.1tie4.54.9tie
ReasoningLlama 3.3 70B Instruct
- GPQA DiamondLlama 3.3 70B Instruct by 742.849.8+7
- Humanity's Last Examtie4.43.6tie
- CritPttie00tie
FactsLlama 3.3 70B Instruct
- AA-Omniscience · AccuracyLlama 3.3 70B Instruct by 612.918.9+6
- Vectara HHEM hallucination ratelower is betterLlama 3.3 70B Instruct by 3.37.44.1+3.3
- AA-Omniscience · Non-hallucinationLlama 3.3 70B Instruct by 1.97.99.8+1.9
Long documentsLlama 3.3 70B Instruct
- AA-LCRLlama 3.3 70B Instruct by 8.47.315.7+8.4
Following instructionsLlama 3.3 70B Instruct
- IFBenchLlama 3.3 70B Instruct by 15.331.847.1+15.3
Other results15 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.
- vectara_avg_summary_lengthGemma 3 27B by 31.896.464.6+31.8
- τ²-Bench Telecom (AA run)Llama 3.3 70B Instruct by 16.110.526.6+16.1
- AA-OmniscienceLlama 3.3 70B Instruct by 13-67.2-54.2+13
- MATHGemma 3 27B by 128977+12
- SimpleQALlama 3.3 70B Instruct by 10.91020.9+10.9
- MMLULlama 3.3 70B Instruct by 9.176.986+9.1
- LiveCodeBenchLlama 3.3 70B Instruct by 3.629.733.3+3.6
- vectara_factual_consistencyLlama 3.3 70B Instruct by 3.392.695.9+3.3
- AA IntelligenceLlama 3.3 70B Instruct by 2.84.97.7+2.8
- Artificial Analysis Coding IndexLlama 3.3 70B Instruct by 1.810.111.9+1.8
- GSM8KGemma 3 27B by 1.795.994.2+1.7
- IFEvalLlama 3.3 70B Instruct by 1.790.492.1+1.7
- MMLU-ProLlama 3.3 70B Instruct by 1.367.668.9+1.3
- vectara_answer_ratetie98.899.5tie
- HumanEvaltie87.888.4tie
Questions people ask
Which is better, Gemma 3 27B or Llama 3.3 70B Instruct?
Llama 3.3 70B Instruct wins five of the six areas where both have results: coding, reasoning, facts, long documents and following instructions. Gemma 3 27B wins none, but costs 83% less. They are level on agents.
Which is better for coding?
Llama 3.3 70B Instruct. It wins 1 of the 3 coding tests both models report; Gemma 3 27B wins none, and 2 are ties.
Which is cheaper?
Gemma 3 27B costs $0.08 per million input tokens and $0.16 per million output tokens; Llama 3.3 70B Instruct costs $0.71 and $0.72. That makes Gemma 3 27B about 83% cheaper for the same work.
How do you compare the two?
We use the 28 benchmark tests both models have published scores on. The verdict counts the 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.