Claude 2vsGPT-5.4 mini
Claude 2 | GPT-5.4 mini | |
|---|---|---|
| Specifications | ||
Context window | 100k | 400k |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 32% |
Supabase coding Supabase Evals · with skillsSupabase's own open benchmark: a coding agent is dropped into a real Supabase project and asked to do real work — set up a schema, fix a broken security policy, debug an Edge Function — and every run is checked against a live Supabase stack. This is the headline number, where the agent has Supabase's own skills loaded, as most people building on Supabase would. The score is the share of scenarios it got right. Higher is better. | — | 78.9% |
Supabase coding Supabase Evals · no skillsThe same Supabase scenarios, but with none of Supabase's skills loaded — so it measures what the model already knows about building on Supabase, rather than how well it follows Supabase's supplied instructions. Higher is better. | — | 73.7% |
Function synthesis HumanEval164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 71.2% | — |
Browser agent BU BenchCan the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | — | 36% |
General knowledge MMLUA 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 78.5% | — |
Grade-school math GSM8KGrade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | 88% | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | — | 1398 |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Jul 11 2023 | Mar 17 2026 |
| Access | Proprietary | Proprietary |
Which is better: Claude 2 or GPT-5.4 mini?
Claude 2 and GPT-5.4 mini don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Claude 2 shipped 980 days before GPT-5.4 mini, so benchmark comparisons should account for the intervening progress.
Context windows are 100k (Claude 2) vs 400k (GPT-5.4 mini).
Direct benchmark comparisons are unavailable — Claude 2 and GPT-5.4 mini don't publish scores on any of the same benchmarks.
Frequently asked questions
Claude 2 was released by Anthropic on Jul 11 2023.
GPT-5.4 mini was released by OpenAI on Mar 17 2026.
Claude 2 has a 100k context window; GPT-5.4 mini has 400k.
Other comparisons
Claude 2vsGemini 3.6 FlashGPT-5.4 minivsGemini 3.6 FlashClaude 2vsMuse Spark 1.2GPT-5.4 minivsMuse Spark 1.2Claude 2vsGrok 4.5GPT-5.4 minivsGrok 4.5Claude 2vsDeepSeek-V4-Flash-0731GPT-5.4 minivsDeepSeek-V4-Flash-0731Claude 2vsMistral Medium 3.5GPT-5.4 minivsMistral Medium 3.5Claude 2vsKimi K3GPT-5.4 minivsKimi K3