Claude Sonnet 4 vs Granite 3.3 8B Instruct
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
Claude Sonnet 4 is the stronger all-rounder.Granite 3.3 8B Instruct is cheaper.
Scores updated · 29 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 thinking20Claude Sonnet 42 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up20Claude Sonnet 42 of 3 tests · 1 tie
- CodingWriting and fixing software20Claude Sonnet 42 of 2 tests
- AgentsCarrying out multi-step tasks on its own10Claude Sonnet 41 of 1 test
- Long documentsFinding answers in very long texts10Claude Sonnet 41 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Sonnet 41 of 1 test
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.
Granite 3.3 8B Instruct costs 98% 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 Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+67.1points ahead
- Reasons across sets of long documentsAA-LCR+67points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+43.9points ahead
Where Granite 3.3 8B Instruct pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 29 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4
- Terminal-Bench HardClaude Sonnet 4 by 31.131.10+31.1
- SciCodeClaude Sonnet 4 by 29.94010.1+29.9
ReasoningClaude Sonnet 4
- GPQA DiamondClaude Sonnet 4 by 43.977.733.8+43.9
- Humanity's Last ExamClaude Sonnet 4 by 6.510.74.2+6.5
- CritPttie0.30tie
FactsClaude Sonnet 4
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 67.170.93.8+67.1
- AA-Omniscience · AccuracyClaude Sonnet 4 by 1322.79.7+13
- Vectara HHEM hallucination ratelower is bettertie10.310.6tie
Following instructionsClaude Sonnet 4
- IFBenchClaude Sonnet 4 by 32.354.722.4+32.3
Other results18 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.
- AA-OmniscienceClaude Sonnet 4 by 77.50.2-77.3+77.5
- τ²-Bench Telecom (AA run)Claude Sonnet 4 by 54.164.610.5+54.1
- AIME 2024Claude Sonnet 4 by 35.343.48.1+35.3
- Artificial Analysis Coding IndexClaude Sonnet 4 by 34.237.63.4+34.2
- MMLUClaude Sonnet 4 by 2691.565.5+26
- MATH-500 (EM)Claude Sonnet 4 by 259469+25
- HarmBenchClaude Sonnet 4 by 16.89881.2+16.8
- AA Agentic IndexClaude Sonnet 4 by 14.117.63.5+14.1
- AA IntelligenceClaude Sonnet 4 by 1418.94.9+14
- IFEvalClaude Sonnet 4 by 12.887.674.8+12.8
- bbqClaude Sonnet 4 by 12.696.684+12.6
- XSTestClaude Sonnet 4 by 5.996.690.7+5.9
- AIR-Bench 2024Claude Sonnet 4 by 5.888.382.5+5.8
- simple_safety_testsClaude Sonnet 4 by 2.510097.5+2.5
- vectara_avg_summary_lengthClaude Sonnet 4 by 14.4 rating points145.8131.4+14.4 rating
- vectara_answer_rateGranite 3.3 8B Instruct by 1.498.6100+1.4
- vectara_factual_consistencytie89.789.4tie
- anthropic_red_teamtie99.299.1tie
Questions people ask
Which is better, Claude Sonnet 4 or Granite 3.3 8B Instruct?
Claude Sonnet 4 wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. Granite 3.3 8B Instruct wins none, but costs 98% less.
Which is better for coding?
Claude Sonnet 4. It wins 2 of the 2 coding tests both models report; Granite 3.3 8B Instruct wins none.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; Granite 3.3 8B Instruct costs $0.03 and $0.25. That makes Granite 3.3 8B Instruct about 98% cheaper for the same work.
How do you compare the two?
We use the 29 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 18 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.