Model comparison
GPT-5.4 Pro vs Inkling-Small
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 46.5 on the Noometry Index. Inkling-Small costs 106× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Last verified . 9 shared benchmarks.
Summary
- They share 9 benchmarks with published results for both. GPT-5.4 Pro scores higher in 3 categories and Inkling-Small in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 38.6.
- The biggest single-benchmark swing is ARC-AGI-2: 83.3% for GPT-5.4 Pro and 40.1% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
- GPT-5.4 Pro accepts more context: 1.05M tokens versus 524K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 Pro | Inkling-Small | |
|---|---|---|
| Provider | OpenAI | Thinking Machines Lab |
| Noometry Index | 58.9 | 46.5 |
| Released | 2026-03-05 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 524K |
| Max output | 128K | 1.05M |
| Input $ / M tokens | $30 | $0.45 |
| Output $ / M tokens | $180 | $1.20 |
| Results tracked | 16 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-5.4 Pro: 43.2 (#90), Inkling-Small: 43.6 (#85)
| Benchmark | GPT-5.4 Pro | Inkling-Small |
|---|---|---|
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| WeirdML | 57.4% | — |
| LMArena Coding | — | 1451 |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 70.7 (#13), Inkling-Small: 38.6 (#63)
| Benchmark | GPT-5.4 Pro | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 83.3% | 40.1% |
| ARC-AGI-1 | 94.5% | 84% |
| CritPt | 30% | 8.3% |
| Chess Puzzles | 58.6% | 18% |
| Epoch Capabilities Index | 158.93 | 150.15 |
| SimpleBench | 74.1% | — |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1423 |
| Mystery Game Puzzles | — | 6% |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.4 (#22), Inkling-Small: 45.1 (#77)
| Benchmark | GPT-5.4 Pro | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | 46.3% |
| FrontierMath Tier 4 | 58.5% | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 90% |
| ProofBench | — | 6% |
| LMArena Math | — | 1459 |
| 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-Small: 48.2 (#77)
| Benchmark | GPT-5.4 Pro | Inkling-Small |
|---|---|---|
| GPQA Diamond | 94.6% | 88.5% |
| SimpleQA Verified | 46.3% | 19.1% |
| Humanity's Last Exam | 44.3% | — |
| Vectara Hallucination Rate | 8.3% | — |
| LMArena Expert | — | 1442 |
Multimodal Not comparable
GPT-5.4 Pro: —, Inkling-Small: 39.1 (#62)
| Benchmark | GPT-5.4 Pro | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
Multilingual Not comparable
GPT-5.4 Pro: —, Inkling-Small: 51.7 (#104)
| Benchmark | GPT-5.4 Pro | Inkling-Small |
|---|---|---|
| LMArena Non-English | — | 1402 |
| LMArena Chinese | — | 1465 |
| LMArena French | — | 1436 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1405 |
| LMArena Korean | — | 1363 |
| LMArena Russian | — | 1391 |
| LMArena Spanish | — | 1428 |
Instruction Following Not comparable
GPT-5.4 Pro: —, Inkling-Small: 73.8 (#114)
| Benchmark | GPT-5.4 Pro | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | — | 1399 |
Long Context Not comparable
GPT-5.4 Pro: —, Inkling-Small: 42.7 (#118)
| Benchmark | GPT-5.4 Pro | Inkling-Small |
|---|---|---|
| LMArena Longer Query | — | 1401 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, Inkling-Small: 59.6 (#107)
| Benchmark | GPT-5.4 Pro | Inkling-Small |
|---|---|---|
| LMArena Text | — | 1414 |
| LMArena Creative Writing | — | 1331 |
| EQ-Bench Creative Writing | — | 1491 |
| LMArena Multi-Turn | — | 1418 |
Frequently asked questions
Is GPT-5.4 Pro better than Inkling-Small?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 46.5 on the Noometry Index. Inkling-Small costs 106× 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-Small?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; GPT-5.4 Pro lists at $30 and $180.
Is GPT-5.4 Pro or Inkling-Small better for coding?
They score almost the same on coding (43.2 vs 43.6); test both on your own repository before choosing.
Which has the bigger context window?
GPT-5.4 Pro does, with 1.05M tokens against 524K.
How many benchmarks do GPT-5.4 Pro and Inkling-Small share?
9 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Inkling-Small has 33.