GPQA Diamond ↗27.18%
GPT-3.5 Turbo (Jan 2024) · GPQA diamond · Best score (across scorers) · % ↗
OpenAI / MODEL EVIDENCE
GPT-3.5 Turbo (Jan 2024)
10 benchmarks · 10 observations · 10 sources · released 2024-01-25
Scores at a glance
10 benchmarks · large dot: GPT-3.5 Turbo (Jan 2024); small dots: closest models where reported
GPT-3.5 Turbo (Jan 2024) · FrontierMath-Tiers-1-3-v2-Private · Best score (across scorers) · % ↗
MATH Level 5 ↗11.63%
GPT-3.5 Turbo (Jan 2024) · MATH level 5 · Best score (across scorers) · % ↗
GPT-3.5 Turbo (Jan 2024) · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % ↗
GPT-3.5 Turbo (Jan 2024) · Mystery Game Puzzles · Best score (across scorers) · % ↗
MMLU ↗67.3%
GPT-3.5 Turbo (Jan 2024) · MMLU · EM · % ↗
WeirdML (v2) ↗3.48%
GPT-3.5 Turbo (Jan 2024) · WeirdML · Accuracy · % ↗
LMCA ↗9.65%
GPT-3.5 Turbo (Jan 2024) · LMCA · Score · % ↗
DTBench ↗48.53%
GPT-3.5 Turbo (Jan 2024) · DTBench · Accuracy · % ↗
Epoch Capabilities Index (ECI) ↗115.68 ECI
GPT-3.5 Turbo (Jan 2024) · General ECI · 26 October 2026 fit ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Llama 3-8B →Meta
3 of 5 shared benchmark comparisons
Claude 2 →Anthropic
3 of 5 shared benchmark comparisons
DeepSeek LLM 67B →DeepSeek
3 of 5 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- DTBench — Conceptual Reasoning Index ↗
- LMCA — Conceptual Reasoning Index ↗
- Holistic Evaluation of Language Models (HELM) ↗
- FrontierMath Tiers 1-3 (v2) ↗
- GPQA Diamond ↗
- MATH Level 5 ↗
- Mystery Game Puzzles ↗
- OTIS Mock AIME 2024-2025 ↗
- AI benchmarks & capabilities ↗
- WeirdML ↗
Names used in source tables
GPT-3.5 Turbo (Jan 2024)