BenchLeader
OpenAI

GPT-5.2 alternatives

Data as of 2 Nov 2026 · ranked on the BenchLeader Index

As of 2 Nov 2026, GPT-5.2 by OpenAI scores 60.1 on the BenchLeader Index at $4.81 per 1M tokens blended. Gemini 3 Pro scores higher (60.2); GPT-6.1 Sol is the best cheaper model within 4 points (67.2 at $4.00); GPT-5.6 Sol is at least 1.5× as fast at a similar score; Kimi K3 is the best open-weights option (62.1).

Scores higher

The closest models above GPT-5.2 on the Index.

Cheaper, nearly as good

Within 4 Index points, for less per token.

Faster

At least 1.5× the output speed, within 4 points.

Open weights

The best models whose weights you can run yourself.

Every alternative side by side

ModelIndex$ / 1M blendedTokens / sWhy
GPT-5.2 (this model)60.1$4.8180–
GPT-6.1 Sol67.2$4.0087cheaper
Gemini 4 Argon65.9$4.0083cheaper
GPT-5.6 Sol65.4$8.00127faster
GPT-6.1 Terra65.2$2.00107cheaper
Claude Sonnet 5.565.1$4.00137cheaper, faster
GPT-6 Sol63.5$4.00149cheaper, faster
Kimi K362.1$6.0066open weights
Qwen3.760.3$3.75203scores higher
Gemini 3 Pro60.2––scores higher
GLM-560.2$1.5562scores higher, open weights
GLM 5.260.1$2.1589open weights

Prices are list prices blended three input tokens to one output; speeds are measured medians, credited on each model page. The Index is BenchLeader's own, from independent benchmarks.

Questions people ask

What is the best alternative to GPT-5.2?
Gemini 3 Pro is the closest model that scores higher on the BenchLeader Index (60.2 against 60.1). For less money, GPT-6.1 Sol scores 67.2 at $4.00 per 1M tokens.
Is there a cheaper alternative to GPT-5.2?
Yes: GPT-6.1 Sol (67.2, $4.00), Gemini 4 Argon (65.9, $4.00) and GPT-6.1 Terra (65.2, $2.00), each within 4 Index points and cheaper than GPT-5.2's $4.81.
Is there an open-source alternative to GPT-5.2?
The best open-weights models on the BenchLeader Index are Kimi K3 (62.1), GLM-5 (60.2) and GLM 5.2 (60.1). You can download and run them yourself; check each licence on its model page.
How are these alternatives chosen?
From the models ranked on the BenchLeader Index today: the ones just above GPT-5.2, cheaper ones within 4 points, ones at least 1.5× as fast within 4 points, and the best open-weights models. Prices are list prices blended three input tokens to one output.

Related: GPT-5.2, alternatives to other models, best value models.