Up to four models
Grok 4.3 Beta vs Gemini 2.5 Pro (Jun 2025)
On the index (GPT-4 = 100), Grok 4.3 Beta scores 146 and Gemini 2.5 Pro (Jun 2025) 145. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
145129–161
WeightsClosed
ReleasedJun 2025
Price in / out$1.25 / $10
Context1.05M
Core tests taken5 of 9
Grok 4.3 Beta and Gemini 2.5 Pro (Jun 2025) are too close to call (1 point apart, within the uncertainty), ahead on 2 of 2 shared core tests.
Test by testthird-party results
Grok 4.3 Beta
Gemini 2.5 Pro (Jun 2025)
Every result as a table
| Test | Grok 4.3 Beta | Gemini 2.5 Pro (Jun 2025) |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 88.8% | 85.3% |
| GeoBench | 56.0% | 81.0% |
| Maths | ||
| FrontierMath (tiers 1-3) | 42.8% | 24.6% |
| AIME-style maths (OTIS mock) | 93.3% | 84.7% |
| FrontierMath (tier 4) | 14.6% | 0.0% |
| Coding | ||
| WeirdML | 49.9% | 54.0% |
| Agents | ||
| DTBench | 90.7% | 82.4% |
| LMCA | 38.3% | 34.8% |
Task length · METR
33 sec
Tests at least two of these models have taken. Bold rows are the core tests.