gpt.buzz
Sign in

Compare models

Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.

Comparing agents instead? Switch to agent compare →

SelectedOpenAI logoGPT-5×xAI logoGrok 4×Mistral logoMistral Large 2×Meta logoLlama 4 Maverick×Clear all
 
OpenAI logoGPT-5

OpenAI

xAI logoGrok 4

xAI

Mistral logoMistral Large 2

Mistral

Meta logoLlama 4 Maverick

Meta

VendorOpenAIxAIMistralMeta
FamilyGPTGrokMistralLlama
Release date2025-08-072025-07-092024-07-242025-04-05
Context window400,000 tokens256,000 tokens128,000 tokens1,000,000 tokens
Parameters——123B400B
Modalitytext, vision, audiotexttexttext, vision
LicenseproprietaryproprietaryMistral Research LicenseLlama 4 Community License
Sourceproprietaryproprietaryopen weightsopen weights
DescriptionOpenAI's flagship general-purpose model. Superseded by GPT-5.5 in April 2026.—Large text-only Mistral model with a 128K context window and 123B parameters, tuned for strong instruction following and long-context reasoning. Mistral's flagship open-weights release in the Large 2 line.Mixture-of-experts open-weight model from Meta.
Links
vendor →
vendor →
vendor →weights →
weights →
Benchmarks
MMLU-Pro85.1%82.8%—80.5%
GPQA-D87.3%87.5%——
HumanEval95.2%—89.0%—
Aider85.4%72.5%——
AIME-2591.0%86.1%——
LiveCB74.5%65.3%——
MMMU74.1%——68.5%

Add a model

Anthropic logoClaude 4.8 OpusmaxAlibaba logoQwen3.7-MaxmaxGoogle logoGemini 3.5maxGoogle logoGemini OmnimaxOpenAI logoGPT-5.5maxAlibaba logoQwen3.6-27BmaxDeepSeek logoDeepSeek-V4-FlashmaxDeepSeek logoDeepSeek-V4-PromaxGoogle logoGemini 3 PromaxAnthropic logoClaude 4.7 OpusmaxAnthropic logoClaude 4.6 SonnetmaxAnthropic logoClaude 4.5 HaikumaxDeepSeek logoDeepSeek-V3.1maxOpenAI logoGPT-5✓xAI logoGrok 4✓Google logoGemini 2.5 FlashmaxAlibaba logoQwen3 235BmaxOpenAI logoo3maxOpenAI logoGPT-4.1maxMeta logoLlama 4 ScoutmaxMeta logoLlama 4 Maverick✓Google logoGemini 2.5 PromaxDeepSeek logoDeepSeek-R1maxMistral logoMistral Large 2✓

Max 4 models. Remove one to add another.