Model comparison
GPT-5.4 Pro vs Inkling
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 44.1 on the Noometry Index. Inkling costs 26× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. GPT-5.4 Pro scores higher in 4 categories and Inkling in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 Pro leads 72.4 to 31.3.
- The biggest single-benchmark swing is FrontierMath Tier 4: 58.5% for GPT-5.4 Pro and 4.9% for Inkling.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
- GPT-5.4 Pro accepts more context: 1.05M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 Pro | Inkling | |
|---|---|---|
| Provider | OpenAI | Thinking Machines Lab |
| Noometry Index | 58.9 | 44.1 |
| Released | 2026-03-05 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 66K |
| Max output | 128K | 66K |
| Input $ / M tokens | $30 | $1.87 |
| Output $ / M tokens | $180 | $4.68 |
| Results tracked | 16 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 Pro leads
GPT-5.4 Pro: 43.2 (#90), Inkling: 34.5 (#234)
| Benchmark | GPT-5.4 Pro | Inkling |
|---|---|---|
| WeirdML | 57.4% | 32.3% |
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1413 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| LMArena Coding | — | 1464 |
| ALE-Bench | — | 946 |
Agentic & Tool Use Not comparable
GPT-5.4 Pro: —, Inkling: 29.6 (#85)
| Benchmark | GPT-5.4 Pro | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 70.7 (#13), Inkling: 40.4 (#56)
| Benchmark | GPT-5.4 Pro | Inkling |
|---|---|---|
| ARC-AGI-2 | 83.3% | 36.5% |
| SimpleBench | 74.1% | 50% |
| ARC-AGI-1 | 94.5% | 79.5% |
| CritPt | 30% | 5.4% |
| Chess Puzzles | 58.6% | 21% |
| Epoch Capabilities Index | 158.93 | 148.54 |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1451 |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.4 (#22), Inkling: 31.3 (#225)
| Benchmark | GPT-5.4 Pro | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | 33.3% |
| FrontierMath Tier 4 | 58.5% | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |
| LMArena Math | — | 1479 |
| FrontierMath (Feb 2025 set) | 50% | — |
| FrontierMath Tier 4 (v1) | 37.5% | — |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#7), Inkling: 55.1 (#49)
| Benchmark | GPT-5.4 Pro | Inkling |
|---|---|---|
| GPQA Diamond | 94.6% | 88.3% |
| SimpleQA Verified | 46.3% | 40.3% |
| Humanity's Last Exam | 44.3% | — |
| Vectara Hallucination Rate | 8.3% | — |
| LMArena Expert | — | 1465 |
Multilingual Not comparable
GPT-5.4 Pro: —, Inkling: 54.0 (#52)
| Benchmark | GPT-5.4 Pro | Inkling |
|---|---|---|
| LMArena Non-English | — | 1434 |
| LMArena Chinese | — | 1490 |
| LMArena French | — | 1458 |
| LMArena German | — | 1446 |
| LMArena Japanese | — | 1429 |
| LMArena Korean | — | 1404 |
| LMArena Russian | — | 1429 |
| LMArena Spanish | — | 1448 |
Instruction Following Not comparable
GPT-5.4 Pro: —, Inkling: 75.1 (#71)
| Benchmark | GPT-5.4 Pro | Inkling |
|---|---|---|
| LMArena Instruction Following | — | 1426 |
Long Context Not comparable
GPT-5.4 Pro: —, Inkling: 43.8 (#86)
| Benchmark | GPT-5.4 Pro | Inkling |
|---|---|---|
| LMArena Longer Query | — | 1434 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, Inkling: 65.2 (#51)
| Benchmark | GPT-5.4 Pro | Inkling |
|---|---|---|
| LMArena Text | — | 1441 |
| LMArena Creative Writing | — | 1387 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
| LMArena Multi-Turn | — | 1436 |
Frequently asked questions
Is GPT-5.4 Pro better than Inkling?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 44.1 on the Noometry Index. Inkling costs 26× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5.4 Pro or Inkling?
Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; GPT-5.4 Pro lists at $30 and $180.
Is GPT-5.4 Pro or Inkling better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 Pro does, with 1.05M tokens against 66K.
How many benchmarks do GPT-5.4 Pro and Inkling share?
11 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Inkling has 41.