Model comparison
GPT-5-Codex vs Inkling
Inkling is the stronger model overall, scoring 44.1 to 37.3 on the Noometry Index.
Last verified . 1 shared benchmarks.
Summary
- They share 1 benchmark with published results for both. GPT-5-Codex scores higher in 2 categories and Inkling in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.6 to 30.0.
- The biggest single-benchmark swing is WeirdML: 54.5% for GPT-5-Codex and 32.3% for Inkling.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- GPT-5-Codex accepts more context: 400K tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| GPT-5-Codex | Inkling | |
|---|---|---|
| Provider | OpenAI | Thinking Machines Lab |
| Noometry Index | 37.3 | 44.1 |
| Released | 2025-09-15 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 400K | 66K |
| Max output | 128K | 66K |
| Input $ / M tokens | $1.25 | $1.87 |
| Output $ / M tokens | $10 | $4.68 |
| Results tracked | 3 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5-Codex leads
GPT-5-Codex: 41.9 (#100), Inkling: 34.1 (#229)
| Benchmark | GPT-5-Codex | Inkling |
|---|---|---|
| WeirdML | 54.5% | 32.3% |
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1412 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| LMArena Coding | — | 1463 |
| ALE-Bench | — | 946 |
Agentic & Tool Use GPT-5-Codex leads
GPT-5-Codex: 30.8 (#66), Inkling: 29.5 (#76)
| Benchmark | GPT-5-Codex | Inkling |
|---|---|---|
| Terminal-Bench | 44.3% | — |
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |
Reasoning Inkling leads
GPT-5-Codex: 30.0 (#80), Inkling: 40.6 (#48)
| Benchmark | GPT-5-Codex | Inkling |
|---|---|---|
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | — | 79.5% |
| CritPt | — | 5.4% |
| Chess Puzzles | — | 21% |
| LMArena Hard Prompts | — | 1452 |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 148.6 |
Math Not comparable
GPT-5-Codex: —, Inkling: 31.2 (#198)
| Benchmark | GPT-5-Codex | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |
| LMArena Math | — | 1482 |
Knowledge Not comparable
GPT-5-Codex: —, Inkling: 55.2 (#44)
| Benchmark | GPT-5-Codex | Inkling |
|---|---|---|
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |
| LMArena Expert | — | 1468 |
Multilingual Not comparable
GPT-5-Codex: —, Inkling: 54.2 (#49)
| Benchmark | GPT-5-Codex | Inkling |
|---|---|---|
| LMArena Non-English | — | 1434 |
| LMArena Chinese | — | 1495 |
| LMArena French | — | 1453 |
| LMArena German | — | 1456 |
| LMArena Japanese | — | 1428 |
| LMArena Korean | — | 1401 |
| LMArena Russian | — | 1430 |
| LMArena Spanish | — | 1442 |
Instruction Following Not comparable
GPT-5-Codex: —, Inkling: 75.3 (#65)
| Benchmark | GPT-5-Codex | Inkling |
|---|---|---|
| LMArena Instruction Following | — | 1427 |
Long Context Not comparable
GPT-5-Codex: —, Inkling: 43.9 (#79)
| Benchmark | GPT-5-Codex | Inkling |
|---|---|---|
| LMArena Longer Query | — | 1436 |
Writing & Preference Not comparable
GPT-5-Codex: —, Inkling: 65.5 (#48)
| Benchmark | GPT-5-Codex | Inkling |
|---|---|---|
| LMArena Text | — | 1443 |
| LMArena Creative Writing | — | 1390 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
| LMArena Multi-Turn | — | 1436 |
Frequently asked questions
Is GPT-5-Codex better than Inkling?
Inkling is the stronger model overall, scoring 44.1 to 37.3 on the Noometry Index.
Which is cheaper, GPT-5-Codex or Inkling?
Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; GPT-5-Codex lists at $1.25 and $10.
Is GPT-5-Codex or Inkling better for coding?
GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5-Codex does, with 400K tokens against 66K.
How many benchmarks do GPT-5-Codex and Inkling share?
1 benchmark has published results for both models. GPT-5-Codex has 3 scored results on Noometry and Inkling has 41.