Noometry

Model comparison

GPT-4 Turbo vs GPT-5.5 Pro

GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 30.5 on the Noometry Index. GPT-4 Turbo costs 4.5× less per token, which makes it the better buy when GPT-5.5 Pro's lead doesn't matter for your workload.

Last verified . 8 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

GPT-5.5 Pro OpenAI

64.3

Rank #8 Confirmed

Summary

  • They share 8 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and GPT-5.5 Pro in 3 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.5 Pro leads 84.0 to 9.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo and 100% for GPT-5.5 Pro.
  • GPT-4 Turbo is cheaper at $10 / $30 per million input/output tokens, against $30 / $180 for GPT-5.5 Pro.
  • GPT-5.5 Pro accepts more context: 1.05M tokens versus 128K.

Side by side

GPT-4 TurboGPT-5.5 Pro
ProviderOpenAIOpenAI
Noometry Index30.564.3
Released2023-11-062026-04-23
WeightsProprietaryProprietary
Context window128K1.05M
Max output4K128K
Input $ / M tokens$10$30
Output $ / M tokens$30$180
Results tracked3614

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

GPT-4 Turbo: 33.8 (#249), GPT-5.5 Pro: —

BenchmarkGPT-4 TurboGPT-5.5 Pro
WeirdML18%—
BigCodeBench Instruct48.2%—
LMArena Coding1268—
BigCodeBench Complete58.2%—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, GPT-5.5 Pro: —

BenchmarkGPT-4 TurboGPT-5.5 Pro
METR Time Horizons36.7%—

Reasoning GPT-5.5 Pro leads

GPT-4 Turbo: 15.3 (#317), GPT-5.5 Pro: 73.3 (#10)

BenchmarkGPT-4 TurboGPT-5.5 Pro
SimpleBench25.1%76.9%
Chess Puzzles6%64%
DTBench61.6%96%
LMCA9.8%53.9%
Epoch Capabilities Index127.25162.07
ARC-AGI-2—84.6%
ARC-AGI-1—96.5%
CritPt—30.6%
LMArena Hard Prompts1251—
ForecastBench59.4—

Math GPT-5.5 Pro leads

GPT-4 Turbo: 9.0 (#322), GPT-5.5 Pro: 84.0 (#10)

BenchmarkGPT-4 TurboGPT-5.5 Pro
FrontierMath (Tiers 1-3)0.7%87.7%
OTIS Mock AIME 2024-20256.7%100%
FrontierMath Tier 4—78%
LMArena Math1272—
MATH Level 546.7%—
FrontierMath (Feb 2025 set)—52.4%
FrontierMath Tier 4 (v1)—39.6%

Knowledge GPT-5.5 Pro leads

GPT-4 Turbo: 24.3 (#268), GPT-5.5 Pro: 64.1 (#19)

BenchmarkGPT-4 TurboGPT-5.5 Pro
GPQA Diamond46.6%93.9%
Confabulations28.4%—
LMArena Expert1223—
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), GPT-5.5 Pro: —

BenchmarkGPT-4 TurboGPT-5.5 Pro
LMArena Vision1090—

Multilingual Not comparable

GPT-4 Turbo: 40.5 (#216), GPT-5.5 Pro: —

BenchmarkGPT-4 TurboGPT-5.5 Pro
LMArena Non-English1245—
LMArena Chinese1242—
LMArena French1276—
LMArena German1259—
LMArena Japanese1194—
LMArena Korean1187—
LMArena Russian1259—
LMArena Spanish1260—

Instruction Following Not comparable

GPT-4 Turbo: 65.8 (#216), GPT-5.5 Pro: —

BenchmarkGPT-4 TurboGPT-5.5 Pro
LMArena Instruction Following1249—

Long Context Not comparable

GPT-4 Turbo: 38.0 (#206), GPT-5.5 Pro: —

BenchmarkGPT-4 TurboGPT-5.5 Pro
LMArena Longer Query1254—

Writing & Preference Not comparable

GPT-4 Turbo: 47.7 (#206), GPT-5.5 Pro: —

BenchmarkGPT-4 TurboGPT-5.5 Pro
LMArena Text1272—
LMArena Creative Writing1269—
LMArena Multi-Turn1267—

Frequently asked questions

Is GPT-4 Turbo better than GPT-5.5 Pro?

GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 30.5 on the Noometry Index. GPT-4 Turbo costs 4.5× less per token, which makes it the better buy when GPT-5.5 Pro's lead doesn't matter for your workload.

Which is cheaper, GPT-4 Turbo or GPT-5.5 Pro?

GPT-4 Turbo is cheaper. It lists at $10 per million input tokens and $30 per million output tokens; GPT-5.5 Pro lists at $30 and $180.

Which has the bigger context window?

GPT-5.5 Pro does, with 1.05M tokens against 128K.

How many benchmarks do GPT-4 Turbo and GPT-5.5 Pro share?

8 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and GPT-5.5 Pro has 14.

Related comparisons

Go deeper