Model comparison
GPT-4 Turbo vs GPT-5.1
GPT-5.1 is the stronger model overall, scoring 49.0 to 30.5 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and GPT-5.1 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.1 leads 52.2 to 9.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo and 88.6% for GPT-5.1.
- GPT-5.1 is cheaper at $1.25 / $10 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- GPT-5.1 accepts more context: 400K tokens versus 128K.
Side by side
| GPT-4 Turbo | GPT-5.1 | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 30.5 | 49.0 |
| Released | 2023-11-06 | 2025-11-13 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 400K |
| Max output | 4K | 128K |
| Input $ / M tokens | $10 | $1.25 |
| Output $ / M tokens | $30 | $10 |
| Results tracked | 36 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
GPT-4 Turbo: 33.8 (#249), GPT-5.1: 46.4 (#66)
| Benchmark | GPT-4 Turbo | GPT-5.1 |
|---|---|---|
| WeirdML | 18% | 60.8% |
| LMArena Coding | 1268 | 1454 |
| SWE-bench Verified | — | 68% |
| SWE-bench Verified (bash only) | — | 66% |
| LMArena WebDev | — | 1395 |
| SciCode | — | 43.3% |
| GSO | — | 13.7% |
| BigCodeBench Instruct | 48.2% | — |
| LiveBench Coding | — | 72.5% |
| BigCodeBench Complete | 58.2% | — |
| ALE-Bench | — | 1,192 |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, GPT-5.1: 32.7 (#60)
| Benchmark | GPT-4 Turbo | GPT-5.1 |
|---|---|---|
| Terminal-Bench | — | 47.6% |
| DeepResearch Bench | — | 42.8% |
| LMArena Search | — | 1199 |
| METR Time Horizons | 36.7% | — |
| Vending-Bench 2 | — | 1,473 |
Reasoning GPT-5.1 leads
GPT-4 Turbo: 15.3 (#317), GPT-5.1: 39.8 (#58)
| Benchmark | GPT-4 Turbo | GPT-5.1 |
|---|---|---|
| SimpleBench | 25.1% | 53.2% |
| Chess Puzzles | 6% | 32% |
| LMArena Hard Prompts | 1251 | 1457 |
| DTBench | 61.6% | 90.1% |
| LMCA | 9.8% | 43.9% |
| Epoch Capabilities Index | 127.25 | 149.64 |
| ForecastBench | 59.4 | 58.1 |
| ARC-AGI-2 | — | 17.6% |
| ARC-AGI-1 | — | 72.8% |
| CritPt | — | 4.9% |
| EnigmaEval | — | 11.2% |
| LiveBench Reasoning | — | 95.8% |
| Mystery Game Puzzles | — | 19% |
| LiveBench Data Analysis | — | 72.1% |
| LiveBench | — | 78.8% |
Math GPT-5.1 leads
GPT-4 Turbo: 9.0 (#322), GPT-5.1: 52.2 (#51)
| Benchmark | GPT-4 Turbo | GPT-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 88.6% |
| LMArena Math | 1272 | 1447 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| Omni-MATH | — | 46.4% |
| LiveBench Math | — | 94.5% |
| MATH Level 5 | 46.7% | — |
| FrontierMath (Feb 2025 set) | — | 31% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge GPT-5.1 leads
GPT-4 Turbo: 24.3 (#268), GPT-5.1: 50.6 (#71)
| Benchmark | GPT-4 Turbo | GPT-5.1 |
|---|---|---|
| GPQA Diamond | 46.6% | 87.6% |
| LMArena Expert | 1223 | 1470 |
| Humanity's Last Exam | — | 23.7% |
| SimpleQA Verified | — | 48% |
| MMLU-Pro | — | 57.9% |
| Confabulations | 28.4% | — |
| Vectara Hallucination Rate | — | 10.9% |
| GPQA (HELM) | — | 44.2% |
| MMLU | 81.3% | — |
Multimodal GPT-5.1 leads
GPT-4 Turbo: 30.6 (#110), GPT-5.1: 44.8 (#19)
| Benchmark | GPT-4 Turbo | GPT-5.1 |
|---|---|---|
| LMArena Vision | 1090 | 1250 |
| VPCT | — | 58.7% |
| LMArena Document | — | 1403 |
Multilingual GPT-5.1 leads
GPT-4 Turbo: 40.5 (#216), GPT-5.1: 53.8 (#56)
| Benchmark | GPT-4 Turbo | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1245 | 1431 |
| LMArena Chinese | 1242 | 1495 |
| LMArena French | 1276 | 1450 |
| LMArena German | 1259 | 1438 |
| LMArena Japanese | 1194 | 1453 |
| LMArena Korean | 1187 | 1401 |
| LMArena Russian | 1259 | 1435 |
| LMArena Spanish | 1260 | 1433 |
Instruction Following GPT-5.1 leads
GPT-4 Turbo: 65.8 (#216), GPT-5.1: 83.9 (#1)
| Benchmark | GPT-4 Turbo | GPT-5.1 |
|---|---|---|
| LMArena Instruction Following | 1249 | 1443 |
| LiveBench Instruction Following | — | 93.3% |
| IFEval | — | 93.5% |
Long Context GPT-5.1 leads
GPT-4 Turbo: 38.0 (#206), GPT-5.1: 47.6 (#14)
| Benchmark | GPT-4 Turbo | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1254 | 1447 |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |
Writing & Preference GPT-5.1 leads
GPT-4 Turbo: 47.7 (#206), GPT-5.1: 64.5 (#55)
| Benchmark | GPT-4 Turbo | GPT-5.1 |
|---|---|---|
| LMArena Text | 1272 | 1443 |
| LMArena Creative Writing | 1269 | 1427 |
| LMArena Multi-Turn | 1267 | 1450 |
| WildBench | — | 86.3% |
| LiveBench Language | — | 80.2% |
Frequently asked questions
Is GPT-4 Turbo better than GPT-5.1?
GPT-5.1 is the stronger model overall, scoring 49.0 to 30.5 on the Noometry Index.
Which is cheaper, GPT-4 Turbo or GPT-5.1?
GPT-5.1 is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is GPT-4 Turbo or GPT-5.1 better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
GPT-5.1 does, with 400K tokens against 128K.
How many benchmarks do GPT-4 Turbo and GPT-5.1 share?
27 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and GPT-5.1 has 63.