Rank coding-capable models using documented task fit, coding benchmark coverage, price, context, and providers.
Interactive Tool
| Result | Value | How to read it |
|---|---|---|
| Eligible models | 23 | Models that pass the selected evidence and constraint gates. |
| Ranked shortlist | 20 | Top candidates shown below. |
| Priced candidates | 17 | Models with both input and output price minima. |
| Rank | Model | Fit score | Context | Input / 1M | Workload cost | Published benchmark rank | Providers |
|---|---|---|---|---|---|---|---|
| 1 | GPT-6.1 SolOpenAI | 79.85 | 1.05M tokens | $2.00 / 1M | $400.00 | 4 | 2 |
| 2 | GPT-6 LunaOpenAI | 79.63 | 1.05M tokens | $0.10 / 1M | $20.00 | 8 | 2 |
| 3 | Gemini 3.8 FlashGoogle DeepMind | 78.91 | 1.05M tokens | $0.75 / 1M | $150.00 | 7 | 2 |
| 4 | InklingThinking Machines Lab | 77.98 | 1.05M tokens | $0.95 / 1M | $176.00 | 11 | 4 |
| 5 | Qwen3.8 MaxQwen | 76.42 | 1M tokens | $1.65 / 1M | $264.02 | 10 | 4 |
| 6 | GLM 5.3 FlashZ.ai | 71 | 1M tokens | $0.08 / 1M | $12.50 | 18 | 4 |
| 7 | Qwen3.7 PlusQwen | 64.57 | 1M tokens | $0.32 / 1M | $57.60 | 23 | 4 |
| 8 | Inkling SmallThinking Machines Lab | 63.69 | 1.05M tokens | $0.45 / 1M | $69.00 | 22 | 2 |
| 9 | GPT-6 AstraOpenAI | 63.01 | 1.05M tokens | $10.00 / 1M | $2,000.00 | 2 | 2 |
| 10 | GLM 5.3Z.ai | 61.37 | 1M tokens | $0.90 / 1M | $170.00 | 25 | 4 |
| 11 | Qwen3.8 FlashQwen | 53.49 | 1M tokens | $0.11 / 1M | $18.94 | 41 | 4 |
| 12 | DeepSeek V4 Pro 0813DeepSeek | 51.73 | 1.05M tokens | $1.30 / 1M | $182.00 | Unknown | 3 |
| 13 | Kimi K2.7 CodeMoonshot AI | 50.69 | 262.14K tokens | $0.67 / 1M | $134.12 | 61 | 4 |
| 14 | Granite 4.2 8BIBM | 49.23 | 131.07K tokens | $0.06 / 1M | $11.00 | 56 | 2 |
| 15 | Granite 4.2 3BIBM | 47.8 | 131.07K tokens | $0.03 / 1M | $5.40 | 59 | 1 |
| 16 | Granite 4.2 30BIBM | 47.5 | 131.07K tokens | $0.16 / 1M | $29.00 | 50 | 1 |
| 17 | GPT-6 SolOpenAI | 47.5 | 1.05M tokens | $2.00 / 1M | $400.00 | Unknown | 2 |
| 18 | BeamReflection AI | 28.5 | 262.14K tokens | Unknown | Unknown | Unknown | 1 |
| 19 | GLM 5V TurboZ.ai | 28.5 | 200K tokens | Unknown | Unknown | Unknown | 1 |
| 20 | Kolibri 1Aleph Alpha | 27 | 1.05M tokens | Unknown | Unknown | Unknown | 0 |
Fit scores are transparent screening aids, not universal quality claims. Unknown capability, context, or price fields are never filled by inference.
Inputs
| Input | How it is used |
|---|---|
| Coding workload | Interactive coding, repository agent, review, or high-context analysis. |
| Context requirement | Repository and conversation envelope. |
| Monthly tokens | Input and output volume for a cost screen. |
| Priority | Balance published performance, cost, and context. |
Candidates need coding-related task or capability evidence, then receive a transparent score from context fit, current price, provider breadth, and published benchmark rank.
Run your own repository tasks before choosing. Coding benchmark rank can miss tool use, edit reliability, instruction following, and agent-loop economics.
Boundaries
Catalog values retain their source and freshness on the linked model, provider, benchmark, or comparison page. Editable scenario assumptions are not Model Markets measurements.
Continue the Analysis
| Tool | Next question |
|---|---|
| Coding Agent Cost | Convert an agent's observed hourly token burn into a monthly cost scenario. |
| Benchmark Comparison | Inspect like-for-like published results without blending incompatible metrics or versions. |
| API vs Subscription | Find the usage level where seat pricing and metered API pricing cross for a team. |
Questions
Shortlist models for code generation, repository agents, review, or debugging under explicit cost and context constraints. It returns coding candidates with fit signals, published rank, context, estimated workload cost, and model links.
Where the calculation needs model facts, it uses the current Model Markets catalog snapshot updated 2026-10-19. User-entered assumptions remain clearly editable, and unsupported values stay unknown rather than being inferred.
Agent harness quality can dominate base-model differences. Output-token verbosity changes both cost and benchmark efficiency. Subscription products can route to models or limits different from API records. Open the linked canonical records and primary sources before making a production or purchasing decision.
