# Chatgpt 4o Latest 20250326 vs Gemini 2.5 Flash

> Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.8 to 39.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/chatgpt-4o-vs-gemini-2-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Chatgpt 4o Latest 20250326 scores higher in 5 categories and Gemini 2.5 Flash in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Chatgpt 4o Latest 20250326 leads 33.8 to 18.1.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 75% for Chatgpt 4o Latest 20250326 and 56.8% for Gemini 2.5 Flash.

## Snapshot

| | Chatgpt 4o Latest 20250326 | Gemini 2.5 Flash |
|---|---|---|
| Provider | OpenAI | Google |
| Noometry Index | 43.8 | 39.3 |
| Rank | 82 | 170 |
| Context | — | 1.05M |
| Input $/M | — | $0.30 |
| Output $/M | — | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Chatgpt 4o Latest 20250326: 41.6 (#122)
- Gemini 2.5 Flash: 35.8 (#220)

| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Coding | 1413 | 1424 |
| SWE-bench Verified (bash only) | — | 28.7% |
| Aider Polyglot | — | 55.1% |
| WeirdML | — | 41.9% |
| ALE-Bench | — | 661.88 |

## Agentic & Tool Use

- Chatgpt 4o Latest 20250326: —
- Gemini 2.5 Flash: 30.8 (#74)

| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 2.5 Flash |
|---|---|---|
| Terminal-Bench | — | 17.1% |
| Berkeley Function Calling Leaderboard | — | 56.2% |
| TheAgentCompany | — | 41.1% |
| BALROG | — | 33.5% |
| Vending-Bench 2 | — | 548.84 |

## Reasoning

- Chatgpt 4o Latest 20250326: 33.8 (#71)
- Gemini 2.5 Flash: 18.1 (#286)

| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 2.5 Flash |
|---|---|---|
| Kagi LLM Benchmark | 75% | 56.8% |
| LMArena Hard Prompts | 1424 | 1422 |
| ARC-AGI-2 | — | 2.5% |
| SimpleBench | — | 41.2% |
| ARC-AGI-1 | — | 33.3% |
| CritPt | — | 1.1% |
| EnigmaEval | — | 2.7% |
| DTBench | — | 76.5% |
| LMCA | — | 27.5% |
| Epoch Capabilities Index | — | 143.03 |
| ForecastBench | — | 60.6 |

## Math

- Chatgpt 4o Latest 20250326: 38.6 (#134)
- Gemini 2.5 Flash: 39.9 (#98)

| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Math | 1407 | 1415 |
| OTIS Mock AIME 2024-2025 | — | 73.1% |
| Omni-MATH | — | 38.5% |
| FrontierMath (Feb 2025 set) | — | 4.8% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Chatgpt 4o Latest 20250326: 39.2 (#137)
- Gemini 2.5 Flash: 36.4 (#168)

| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 2.5 Flash |
|---|---|---|
| Confabulations | 16.6% | 16.8% |
| LMArena Expert | 1401 | 1426 |
| Humanity's Last Exam | — | 12.1% |
| MMLU-Pro | — | 63.9% |
| Vectara Hallucination Rate | — | 7.8% |
| GPQA (HELM) | — | 39% |

## Multimodal

- Chatgpt 4o Latest 20250326: 39.6 (#58)
- Gemini 2.5 Flash: 41.8 (#32)

| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Vision | 1243 | 1253 |
| GeoBench | — | 76% |
| VPCT | — | 46.2% |
| SpatialViz-Bench | — | 36.9% |

## Multilingual

- Chatgpt 4o Latest 20250326: 52.9 (#76)
- Gemini 2.5 Flash: 52.3 (#88)

| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1419 | 1409 |
| LMArena Chinese | 1457 | 1450 |
| LMArena French | 1446 | 1433 |
| LMArena German | 1423 | 1418 |
| LMArena Japanese | 1405 | 1405 |
| LMArena Korean | 1396 | 1385 |
| LMArena Russian | 1429 | 1415 |
| LMArena Spanish | 1434 | 1421 |

## Instruction Following

- Chatgpt 4o Latest 20250326: 74.0 (#107)
- Gemini 2.5 Flash: 75.7 (#54)

| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1403 | 1405 |
| IFEval | — | 89.8% |

## Long Context

- Chatgpt 4o Latest 20250326: 43.1 (#107)
- Gemini 2.5 Flash: 47.5 (#17)

| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Longer Query | 1413 | 1419 |
| Fiction.LiveBench | — | 77.8% |

## Writing & Preference

- Chatgpt 4o Latest 20250326: 62.6 (#72)
- Gemini 2.5 Flash: 53.8 (#157)

| Benchmark | Chatgpt 4o Latest 20250326 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1429 | 1417 |
| LMArena Creative Writing | 1405 | 1400 |
| EQ-Bench Creative Writing | 1501 | 1137 |
| LMArena Multi-Turn | 1454 | 1408 |
| Short-Story Creative Writing | — | 76.5% |
| WildBench | — | 81.7% |

## FAQ

### Is Chatgpt 4o Latest 20250326 better than Gemini 2.5 Flash?

Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.8 to 39.3 on the Noometry Index.

### Is Chatgpt 4o Latest 20250326 or Gemini 2.5 Flash better for coding?

Chatgpt 4o Latest 20250326 scores higher on coding benchmarks: 41.6 versus 35.8 in the Noometry coding category.

### How many benchmarks do Chatgpt 4o Latest 20250326 and Gemini 2.5 Flash share?

21 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and Gemini 2.5 Flash has 54.