Compare · ModelsLive · 2 picked · head to head
Claude Sonnet 4.5 vs GPT-3.5 Turbo (older v0613)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Sonnet 4.5 wins on 9/9 benchmarks
Claude Sonnet 4.5 wins 9 of 9 shared benchmarks. Leads in knowledge · general · math.
Category leads
knowledge·Claude Sonnet 4.5general·Claude Sonnet 4.5math·Claude Sonnet 4.5coding·Claude Sonnet 4.5
Hype vs Reality
Attention vs performance
Claude Sonnet 4.5
#213 by perf·#12 by attention
GPT-3.5 Turbo (older v0613)
#243 by perf·no signal
Best value
GPT-3.5 Turbo (older v0613)
5.2x better value than Claude Sonnet 4.5
Claude Sonnet 4.5
4.2 pts/$
$9.00/M
GPT-3.5 Turbo (older v0613)
21.9 pts/$
$1.50/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
9 benchmarks · 2 models
Claude Sonnet 4.5GPT-3.5 Turbo (older v0613)
Chess Puzzles
Claude Sonnet 4.5 leads by +5.3
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Sonnet 4.5
5.3
GPT-3.5 Turbo (older v0613)
0.0
Dtbench
Claude Sonnet 4.5 leads by +57.8
Claude Sonnet 4.5
72.0
GPT-3.5 Turbo (older v0613)
14.2
FrontierMath-Tiers-1-3-v2-Private
Claude Sonnet 4.5 leads by +23.9
Claude Sonnet 4.5
23.9
GPT-3.5 Turbo (older v0613)
0.0
GPQA diamond
Claude Sonnet 4.5 leads by +73.5
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Sonnet 4.5
76.4
GPT-3.5 Turbo (older v0613)
2.9
Lmca
Claude Sonnet 4.5 leads by +34.3
Claude Sonnet 4.5
45.6
GPT-3.5 Turbo (older v0613)
11.3
MATH level 5
Claude Sonnet 4.5 leads by +86.1
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Claude Sonnet 4.5
97.7
GPT-3.5 Turbo (older v0613)
11.6
Mystery Game Puzzles
Claude Sonnet 4.5 leads by +8.6
Claude Sonnet 4.5
8.6
GPT-3.5 Turbo (older v0613)
0.0
OTIS Mock AIME 2024-2025
Claude Sonnet 4.5 leads by +75.6
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Sonnet 4.5
77.8
GPT-3.5 Turbo (older v0613)
2.1
WeirdML
Claude Sonnet 4.5 leads by +44.2
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Sonnet 4.5
47.7
GPT-3.5 Turbo (older v0613)
3.5
Full benchmark table
| Benchmark | Claude Sonnet 4.5 | GPT-3.5 Turbo (older v0613) |
|---|---|---|
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 5.3 | 0.0 |
Dtbench | 72.0 | 14.2 |
FrontierMath-Tiers-1-3-v2-Private | 23.9 | 0.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 76.4 | 2.9 |
Lmca | 45.6 | 11.3 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 97.7 | 11.6 |
Mystery Game Puzzles | 8.6 | 0.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 77.8 | 2.1 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 47.7 | 3.5 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $3.00 | $15.00 | 1.0M tokens (~500 books) | $60.00 | |
| $1.00 | $2.00 | 4K tokens (~2 books) | $12.50 |