Model comparison
Chatgpt 4o Latest 20250326 vs Gemini 3 Deep Think
Chatgpt 4o Latest 20250326 has enough public results to be ranked (#84); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
GoogleSummary
- The widest gap is in reasoning, where Gemini 3 Deep Think leads 70.8 to 32.8.
Side by side
| Chatgpt 4o Latest 20250326 | Gemini 3 Deep Think | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 43.2 | 58.5 |
| Released | — | 2026-02-12 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Chatgpt 4o Latest 20250326: 41.0 (#122), Gemini 3 Deep Think: —
| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 3 Deep Think |
|---|---|---|
| LMArena Coding | 1413 | — |
Reasoning Gemini 3 Deep Think leads
Chatgpt 4o Latest 20250326: 32.8 (#64), Gemini 3 Deep Think: 70.8 (#11)
| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 3 Deep Think |
|---|---|---|
| ARC-AGI-2 | — | 84.6% |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | — | 96% |
| CritPt | — | 25.7% |
| LMArena Hard Prompts | 1424 | — |
Math Not comparable
Chatgpt 4o Latest 20250326: 35.8 (#134), Gemini 3 Deep Think: —
| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 3 Deep Think |
|---|---|---|
| LMArena Math | 1407 | — |
Knowledge Not comparable
Chatgpt 4o Latest 20250326: 38.7 (#131), Gemini 3 Deep Think: —
| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 3 Deep Think |
|---|---|---|
| Confabulations | 16.6% | — |
| LMArena Expert | 1400 | — |
Multimodal Not comparable
Chatgpt 4o Latest 20250326: 38.9 (#54), Gemini 3 Deep Think: —
| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 3 Deep Think |
|---|---|---|
| LMArena Vision | 1243 | — |
Multilingual Not comparable
Chatgpt 4o Latest 20250326: 53.1 (#72), Gemini 3 Deep Think: —
| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 3 Deep Think |
|---|---|---|
| LMArena Non-English | 1419 | — |
| LMArena Chinese | 1456 | — |
| LMArena French | 1447 | — |
| LMArena German | 1424 | — |
| LMArena Japanese | 1406 | — |
| LMArena Korean | 1397 | — |
| LMArena Russian | 1429 | — |
| LMArena Spanish | 1435 | — |
Instruction Following Not comparable
Chatgpt 4o Latest 20250326: 74.2 (#102), Gemini 3 Deep Think: —
| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 3 Deep Think |
|---|---|---|
| LMArena Instruction Following | 1403 | — |
Long Context Not comparable
Chatgpt 4o Latest 20250326: 43.1 (#104), Gemini 3 Deep Think: —
| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 3 Deep Think |
|---|---|---|
| LMArena Longer Query | 1413 | — |
Writing & Preference Not comparable
Chatgpt 4o Latest 20250326: 62.8 (#68), Gemini 3 Deep Think: —
| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 3 Deep Think |
|---|---|---|
| LMArena Text | 1429 | — |
| LMArena Creative Writing | 1406 | — |
| EQ-Bench Creative Writing | 1501 | — |
| LMArena Multi-Turn | 1454 | — |
Frequently asked questions
Is Chatgpt 4o Latest 20250326 better than Gemini 3 Deep Think?
Chatgpt 4o Latest 20250326 has enough public results to be ranked (#84); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
How many benchmarks do Chatgpt 4o Latest 20250326 and Gemini 3 Deep Think share?
0 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and Gemini 3 Deep Think has 3.