Capability ranking
Use this coding AI model leaderboard to compare the current ranking from the LLMBoard Coding Score, aggregated across eligible coding and tool-use benchmarks.
Updated 2026-09-08
This leaderboard ranking orders models by their LLMBoard Coding Score aggregated from eligible benchmark evidence.
Rank | Model | LLMBoard Coding Score | Official input / 1M | Official output / 1M | Output speed | Context |
|---|
| Rank01 | ModelAN | LLMBoard Coding Score98.82 | Official input / 1MN/A | Official output / 1MN/A | Output speedN/A | ContextN/A |
| Rank02 | ModelOP | LLMBoard Coding Score94.72 | Official input / 1M$10 | Official output / 1M$50 | Output speed30.66 tok/s | Context1.1M |
| Rank03 | ModelAN | LLMBoard Coding Score91.86 | Official input / 1M$10 | Official output / 1M$50 | Output speed43.18 tok/s | Context1M |
| Rank04 | ModelOP | LLMBoard Coding Score88.93 | Official input / 1M$4 | Official output / 1M$20 | Output speed2.36 tok/s | Context1.1M |
| Rank05 | ModelMA | LLMBoard Coding Score88.17 | Official input / 1M$3 | Official output / 1M$15 | Output speedN/A | Context1M |
| Rank06 | ModelTE | LLMBoard Coding Score84.65 | Official input / 1MN/A | Official output / 1MN/A | Output speedN/A | ContextN/A |
| Rank07 | ModelAN | LLMBoard Coding Score84.58 | Official input / 1M$5 | Official output / 1M$25 | Output speed62.88 tok/s | Context1M |
| Rank08 | ModelAN | LLMBoard Coding Score83.59 | Official input / 1M$5 | Official output / 1M$25 | Output speed42.00 tok/s | Context1M |
| Rank09 | ModelZA | LLMBoard Coding Score83.02 | Official input / 1M$1.4 | Official output / 1M$4.4 | Output speed472.69 tok/s | Context1M |
| Rank10 | ModelDE | LLMBoard Coding Score81.21 | Official input / 1MN/A | Official output / 1MN/A | Output speed45.48 tok/s | Context1M |
| Rank11 | ModelAC | LLMBoard Coding Score80.86 | Official input / 1M$2.5 | Official output / 1M$7.5 | Output speedN/A | Context1M |
| Rank12 | ModelAN | LLMBoard Coding Score75.26 | Official input / 1M$2 | Official output / 1M$10 | Output speed42.00 tok/s | Context1M |
| Rank13 | ModelAC | LLMBoard Coding Score74.81 | Official input / 1MN/A | Official output / 1MN/A | Output speedN/A | ContextN/A |
| Rank14 | ModelAC | LLMBoard Coding Score74.81 | Official input / 1M$0.15 | Official output / 1M$0.47 | Output speedN/A | Context1M |
| Rank15 | ModelOP | LLMBoard Coding Score74.07 | Official input / 1M$2 | Official output / 1M$12 | Output speed99.35 tok/s | Context1.1M |
| Rank16 | ModelAN | LLMBoard Coding Score72.57 | Official input / 1M$5 | Official output / 1M$25 | Output speed123.15 tok/s | Context1M |
| Rank17 | ModelAC | LLMBoard Coding Score71.34 | Official input / 1M$2 | Official output / 1M$6 | Output speed60.87 tok/s | Context1M |
| Rank18 | ModelOP | LLMBoard Coding Score71.24 | Official input / 1M$5 | Official output / 1M$30 | Output speed134.94 tok/s | Context1.1M |
| Rank19 | ModelAN | LLMBoard Coding Score70.19 | Official input / 1M$5 | Official output / 1M$25 | Output speed42.00 tok/s | Context1M |
| Rank20 | ModelMA | LLMBoard Coding Score69.83 | Official input / 1M$0.95 | Official output / 1M$4 | Output speed1.24 tok/s | Context262.1K |
| Rank21 | ModelOP | LLMBoard Coding Score68.73 | Official input / 1MN/A | Official output / 1MN/A | Output speedN/A | ContextN/A |
| Rank22 | ModelGO | LLMBoard Coding Score68.41 | Official input / 1M$0.75 | Official output / 1M$3.75 | Output speed117.86 tok/s | Context1M |
| Rank23 | ModelZA | LLMBoard Coding Score67.93 | Official input / 1M$0.075 | Official output / 1M$0.25 | Output speed74.28 tok/s | Context1M |
| Rank24 | ModelAC | LLMBoard Coding Score67.88 | Official input / 1MN/A | Official output / 1MN/A | Output speed44.00 tok/s | Context128K |
| Rank25 | ModelAM | LLMBoard Coding Score66.95 | Official input / 1MN/A | Official output / 1MN/A | Output speedN/A | ContextN/A |
| Rank26 | ModelDE | LLMBoard Coding Score65.82 | Official input / 1M$0.14 | Official output / 1M$0.28 | Output speed15.91 tok/s | Context1M |
| Rank27 | ModelOP | LLMBoard Coding Score65.31 | Official input / 1M$0.20 | Official output / 1M$1.2 | Output speed41.87 tok/s | Context1.1M |
| Rank28 | ModelAC | LLMBoard Coding Score63.33 | Official input / 1M$1.4 | Official output / 1M$5.6 | Output speed10.00 tok/s | Context131.1K |
| Rank29 | ModelXI | LLMBoard Coding Score63.07 | Official input / 1M$0.435 | Official output / 1M$0.87 | Output speedN/A | Context1M |
| Rank30 | ModelMI | LLMBoard Coding Score62.32 | Official input / 1M$0.30 | Official output / 1M$1.2 | Output speed100.00 tok/s | Context1M |
Official PAYG prices appear here. Third-party offers remain on the pricing and model detail pages.
Key findings from the current coding leaderboard ranking and its supporting benchmark coverage.
Claude Mythos leads this page at 98.82, 4.10 points ahead of GPT-6-Astra.
Kimi K3 is the highest-ranked open-weight option at #5. GLM 5.3 Flash has the lowest official input price among ranked models.
The leading coding scores in this benchmark-backed ranking, with the axis focused on the competitive leaderboard range.
Compare coding benchmark strength with each model's broader capability score and leaderboard position.
Official vendor API prices plotted against the coding metric used on this page. Price remains a separate decision signal.
Vendor concentration and model access among the first 25 products in the ranking.
A data-backed look at the first five models in this coding leaderboard ranking, including benchmark context, price and output speed where available.
Common questions about the Best AI for Coding leaderboard, benchmark evidence and ranking method.
Claude Mythos is currently ranked first with a coding score of 98.82.
The current leaders are Claude Mythos (98.82 LLMBoard Coding Score), GPT-6-Astra (94.72 LLMBoard Coding Score), and Claude Fable 5 (91.86 LLMBoard Coding Score).
GLM 5.3 Flash has the lowest current official input price among ranked models at $0.08 per 1M tokens.
The fastest matched records are GLM 5.3 (472.69 tok/s via FriendliAI), Gemini 3.5 Flash (210.94 tok/s via Google), and GPT-5.5 (134.94 tok/s via OpenAI).
Kimi K3 is the highest-ranked open-weight model at rank #5.
GPT-6-Astra has the largest listed context window at 1.1M tokens.
Each model appears once using its current scored version. The leaderboard ranking follows the capability named in the title, while the overall page uses the LLMBoard score aggregated from eligible benchmark evidence.
This page currently ranks 99 unique model products.
Main price columns use the model vendor's official standard PAYG API rate. Eligible third-party offers appear only in separately labeled columns, and unavailable official prices display as N/A.
No. Arena results are displayed as an independent signal and are not included in the current LLMBoard capability score.
Ranking basisThis coding AI model leaderboard uses the coding capability score shown on this page. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
Selection summary
Claude Mythos is currently the best-ranked LLM for coding with a 98.82 coding score. The score is a relative ranking signal, so price, speed, context and evidence coverage should still be checked separately.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.