Model comparison
Chatgpt 4o Latest 20250326 vs GPT-5.4
GPT-5.4 is the stronger model overall, scoring 59.5 to 43.2 on the Noometry Index.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. Chatgpt 4o Latest 20250326 scores higher in 0 categories and GPT-5.4 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 leads 73.3 to 35.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 75% for Chatgpt 4o Latest 20250326 and 63.8% for GPT-5.4.
Side by side
| Chatgpt 4o Latest 20250326 | GPT-5.4 | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 43.2 | 59.5 |
| Released | — | 2026-03-05 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $15 |
| Results tracked | 21 | 68 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 leads
Chatgpt 4o Latest 20250326: 41.0 (#122), GPT-5.4: 52.8 (#28)
| Benchmark | Chatgpt 4o Latest 20250326 | GPT-5.4 |
|---|---|---|
| LMArena Coding | 1413 | 1497 |
| SWE-bench Verified | — | 76.9% |
| DeepSWE | — | 51.8% |
| LMArena WebDev | — | 1465 |
| SciCode | — | 56.6% |
| GSO | — | 31.4% |
| WeirdML | — | 77.7% |
| MirrorCode | — | 15.6% |
| ALE-Bench | — | 1,607 |
| AlgoTune | — | 1.85 |
Agentic & Tool Use Not comparable
Chatgpt 4o Latest 20250326: —, GPT-5.4: 46.5 (#12)
| Benchmark | Chatgpt 4o Latest 20250326 | GPT-5.4 |
|---|---|---|
| Terminal-Bench | — | 81.8% |
| APEX-Agents | — | 52.4% |
| τ²-bench Banking | — | 39.4% |
| DeepResearch Bench | — | 35.1% |
| PostTrainBench | — | 19% |
| GBAEval | — | 45.1% |
| LMArena Search | — | 1197 |
| METR Time Horizons | — | 74.3% |
| Vending-Bench 2 | — | 6,144 |
Reasoning GPT-5.4 leads
Chatgpt 4o Latest 20250326: 32.8 (#64), GPT-5.4: 61.7 (#17)
| Benchmark | Chatgpt 4o Latest 20250326 | GPT-5.4 |
|---|---|---|
| Kagi LLM Benchmark | 75% | 63.8% |
| LMArena Hard Prompts | 1424 | 1485 |
| ARC-AGI-2 | — | 74% |
| NYT Connections (extended) | — | 91.3% |
| ARC-AGI-1 | — | 93.7% |
| CritPt | — | 23.4% |
| Chess Puzzles | — | 44% |
| EnigmaEval | — | 16% |
| Thematic Generalization | — | 80% |
| EBR-Bench | — | 25.4% |
| Mystery Game Puzzles | — | 37% |
| DTBench | — | 94.4% |
| LMCA | — | 52% |
| Epoch Capabilities Index | — | 156.92 |
| ForecastBench | — | 59.5 |
Math GPT-5.4 leads
Chatgpt 4o Latest 20250326: 35.8 (#134), GPT-5.4: 73.3 (#14)
| Benchmark | Chatgpt 4o Latest 20250326 | GPT-5.4 |
|---|---|---|
| LMArena Math | 1407 | 1488 |
| FrontierMath (Tiers 1-3) | — | 78.6% |
| FrontierMath Tier 4 | — | 49% |
| MathArena Final-Answer Competitions | — | 83.1% |
| OTIS Mock AIME 2024-2025 | — | 97.8% |
| ProofBench | — | 56% |
| FrontierMath (Feb 2025 set) | — | 47.6% |
| FrontierMath Tier 4 (v1) | — | 27.1% |
Knowledge GPT-5.4 leads
Chatgpt 4o Latest 20250326: 38.7 (#131), GPT-5.4: 65.3 (#13)
| Benchmark | Chatgpt 4o Latest 20250326 | GPT-5.4 |
|---|---|---|
| LMArena Expert | 1400 | 1507 |
| GPQA Diamond | — | 93.3% |
| Humanity's Last Exam | — | 36.2% |
| SimpleQA Verified | — | 45.1% |
| Confabulations | 16.6% | — |
| Vectara Hallucination Rate | — | 7% |
Multimodal GPT-5.4 leads
Chatgpt 4o Latest 20250326: 38.9 (#54), GPT-5.4: 43.8 (#19)
| Benchmark | Chatgpt 4o Latest 20250326 | GPT-5.4 |
|---|---|---|
| LMArena Vision | 1243 | 1302 |
| Blueprint-Bench 2 | — | 27.1% |
| Furniture Assembly | — | 37.5% |
| LMArena Document | — | 1471 |
Multilingual GPT-5.4 leads
Chatgpt 4o Latest 20250326: 53.1 (#72), GPT-5.4: 56.4 (#22)
| Benchmark | Chatgpt 4o Latest 20250326 | GPT-5.4 |
|---|---|---|
| LMArena Non-English | 1419 | 1465 |
| LMArena Chinese | 1456 | 1520 |
| LMArena French | 1447 | 1493 |
| LMArena German | 1424 | 1472 |
| LMArena Japanese | 1406 | 1484 |
| LMArena Korean | 1397 | 1449 |
| LMArena Russian | 1429 | 1480 |
| LMArena Spanish | 1435 | 1453 |
Instruction Following GPT-5.4 leads
Chatgpt 4o Latest 20250326: 74.2 (#102), GPT-5.4: 77.3 (#25)
| Benchmark | Chatgpt 4o Latest 20250326 | GPT-5.4 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1469 |
Long Context GPT-5.4 leads
Chatgpt 4o Latest 20250326: 43.1 (#104), GPT-5.4: 50.3 (#8)
| Benchmark | Chatgpt 4o Latest 20250326 | GPT-5.4 |
|---|---|---|
| LMArena Longer Query | 1413 | 1474 |
| CL-bench | — | 27.9% |
| CL-bench Life | — | 21.7% |
Writing & Preference GPT-5.4 leads
Chatgpt 4o Latest 20250326: 62.8 (#68), GPT-5.4: 72.1 (#18)
| Benchmark | Chatgpt 4o Latest 20250326 | GPT-5.4 |
|---|---|---|
| LMArena Text | 1429 | 1469 |
| LMArena Creative Writing | 1406 | 1439 |
| EQ-Bench Creative Writing | 1501 | 1840 |
| LMArena Multi-Turn | 1454 | 1482 |
| EQ-Bench 4 | — | 1272 |
Frequently asked questions
Is Chatgpt 4o Latest 20250326 better than GPT-5.4?
GPT-5.4 is the stronger model overall, scoring 59.5 to 43.2 on the Noometry Index.
Is Chatgpt 4o Latest 20250326 or GPT-5.4 better for coding?
GPT-5.4 scores higher on coding benchmarks: 52.8 versus 41.0 in the Noometry coding category.
How many benchmarks do Chatgpt 4o Latest 20250326 and GPT-5.4 share?
20 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and GPT-5.4 has 68.