Model card
GPT-4 Turbo (2024).
OpenAIproprietaryUnknown paramsGPT-4 Turbo (gpt-4-turbo-2024-04-09)
GPT-4 Turbo evaluated on METR autonomy tasks and HCAST.
§ 01 · Benchmarks
Every benchmark GPT-4 Turbo (2024) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | METR Time Horizon | Agentic AI · Time Horizon | task-horizon-minutes | 2.0% | #5 | 2025-04-01 | source ↗ |
| 02 | RE-Bench | Agentic AI · RE-Bench | normalized-score | 0.1% | #5 | 2024-11-22 | source ↗ |
| 03 | HCAST | Agentic AI · HCAST | success-rate | 12.0% | #6 | 2023-12-19 | source ↗ |
| 04 | WebArena | Agentic AI · Web & Desktop Agents | success-rate | 14.9% | #6 | 2023-07-26 | source ↗ |
| 05 | OSWorld | Agentic AI · Web & Desktop Agents | success-rate | 6.5% | #13 | 2024-04-11 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where GPT-4 Turbo (2024) actually performs.
§ 03 · Papers
5 papers with results for GPT-4 Turbo (2024).
- 2025-04-01· Agentic AI· 1 result
METR: Measuring Autonomy in AI Systems (2025 Update)
- 2024-11-22· Agentic AI· 1 result
RE-Bench: Evaluating Frontier AI R&D Capabilities of Language Model Agents Against Human Experts
- 2024-04-11· Agentic AI· 1 result
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
- 2023-12-19· Agentic AI· 1 result
HCAST: Human-Calibrated Autonomy Software Tasks
- 2023-07-26· Agentic AI· 1 result
WebArena: A Realistic Web Environment for Building Autonomous Agents
§ 04 · Related models
Other OpenAI models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
3
results
official-leaderboard
2
results
5 of 5 rows marked verified. · first result 2023-07-26, latest 2025-04-01.