Task results
Recent competitive programming problems (LCB, English questions)
Has the model write code for recent problems from competitive programming sites and checks whether it passes the tests.
How to read this table
- Higher rows are rated higher. A range like “1–2” means the gap is within the margin of error.
- The score is the share of a shared set of problems the model solved (%).
- A gap of 3 means 3 problems out of 100.
- Prices are a guide per million tokens, reading then writing.
- Length is how much text the model can read at once (tokens).
| Rank | Model | Developer | Accuracy (%) | Evaluated | Input $ /1M | Output $ /1M | Context | Supports | Weights | Released | Price and specs |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Gemma 4 31B | Rating 81.0 | — | — | 262.1K | Google Released 2026-04 Price — Length 262.1K | |||||
| 2 | Gemma 4 26B A4B | Rating 75.5 | $0.15 | $0.6 | 262.1K | Google Released 2026-04 Price $0.15 / $0.6 Length 262.1K | |||||
| 3 | Qwen3 235B A22B (thinking) | Alibaba | Rating 73.1 | — | — | 262.1K | Alibaba Released 2025-07 Price — Length 262.1K | ||||
| 4 | GPT-5.4 | OpenAI | Rating 72.3 | $2.5 | $15 | 1.05M | OpenAI Released 2026-03 Price $2.5 / $15 Length 1.05M | ||||
| 5 | GPT-OSS-Swallow-120B-RL-v0.1 | Swallow (Science Tokyo) | Rating 71.1 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 6 | NVIDIA Nemotron 3 Super 120B A12B | NVIDIA | Rating 69.1 | — | — | 262.1K | NVIDIA Released 2026-03 Price — Length 262.1K | ||||
| 7 | Qwen3 Next 80B A3B | Alibaba | Rating 68.3 | $0.5 | $6 | 131.1K | Alibaba Released 2025-09 Price $0.5 / $6 Length 131.1K | ||||
| 8 | GPT-5 mini | OpenAI | Rating 67.8 | $0.25 | $2 | 400K | OpenAI Released 2025-08 Price $0.25 / $2 Length 400K | ||||
| 9 | GPT-5 | OpenAI | Rating 67.6 | $1.25 | $10 | 400K | OpenAI Released 2025-08 Price $1.25 / $10 Length 400K | ||||
| 10 | GPT-OSS-Swallow-20B-RL-v0.1 | Swallow (Science Tokyo) | Rating 66.5 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 11 | o3 | OpenAI | Rating 64.9 | $2 | $8 | 200K | OpenAI Released 2025-04 Price $2 / $8 Length 200K | ||||
| 12 | GPT-OSS 120B | OpenAI | Rating 64.7 | — | — | 128K | OpenAI Released 2025-08 Price — Length 128K | ||||
| 13–14 | Qwen3.5 122B A10B | Alibaba | Rating 63.8 | $0.4 | $3.2 | 262.1K | Alibaba Released 2026-02 Price $0.4 / $3.2 Length 262.1K | ||||
| 13–14 | Qwen3-Swallow-32B-RL-v0.2 | Swallow (Science Tokyo) | Rating 63.8 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 15 | Qwen3.5 27B | Alibaba | Rating 63.5 | $0.3 | $2.4 | 262.1K | Alibaba Released 2026-02 Price $0.3 / $2.4 Length 262.1K | ||||
| 16 | GPT-OSS-Swallow-120B-SFT-v0.1 | Swallow (Science Tokyo) | Rating 63.4 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 17 | Qwen3-Swallow-30B-A3B-RL-v0.2 | Swallow (Science Tokyo) | Rating 61.8 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 18 | GPT-OSS 20B | OpenAI | Rating 59.9 | — | — | 131K | OpenAI Released 2025-08 Price — Length 131K | ||||
| 19 | GPT-OSS-Swallow-20B-SFT-v0.1 | Swallow (Science Tokyo) | Rating 58.9 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 20 | Qwen3.5 35B A3B | Alibaba | Rating 58.4 | $0.25 | $2 | 262.1K | Alibaba Released 2026-02 Price $0.25 / $2 Length 262.1K | ||||
| 21–22 | Qwen3 30B A3B | Alibaba | Rating 57.3 | — | — | 128K | Alibaba Released 2025-04 Price — Length 128K | ||||
| 21–22 | Qwen3 32B | Alibaba | Rating 57.3 | $0.7 | $2.8 | 131.1K | Alibaba Released 2025-04 Price $0.7 / $2.8 Length 131.1K | ||||
| 23 | OLMo 3 32B Think | Ai2 | Rating 56.9 | — | — | — | — | Ai2 Released — Price — Length — | |||
| 24 | Qwen3 Next 80B A3B (instruct) | Alibaba | Rating 55.9 | $0.5 | $2 | 129K | Alibaba Released 2025-09 Price $0.5 / $2 Length 129K | ||||
| 25 | Qwen3 14B | Alibaba | Rating 55.7 | $0.35 | $1.4 | 131.1K | Alibaba Released 2025-04 Price $0.35 / $1.4 Length 131.1K | ||||
| 26 | Gemma 4 E4B | Rating 54.1 | — | — | 131.1K | — | — | Google Released — Price — Length 131.1K | |||
| 27 | Qwen3-Swallow-32B-SFT-v0.2 | Swallow (Science Tokyo) | Rating 53.7 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 28 | Qwen3-Swallow-32B-CPT-v0.2 | Swallow (Science Tokyo) | Rating 53.2 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 29 | ABEJA-QwQ32b-Reasoning-Japanese-v1.0 | ABEJA | Rating 52.9 | — | — | — | — | — | ABEJA Released — Price — Length — | ||
| 30 | Qwen3-Swallow-8B-RL-v0.2 | Swallow (Science Tokyo) | Rating 52.1 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 31 | Qwen3-Swallow-30B-A3B-SFT-v0.2 | Swallow (Science Tokyo) | Rating 50.5 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 32 | o3-mini | OpenAI | Rating 50.3 | $1.1 | $4.4 | 200K | OpenAI Released 2025-01 Price $1.1 / $4.4 Length 200K | ||||
| 33 | Qwen3 8B | Alibaba | Rating 50.2 | $0.18 | $0.7 | 131.1K | Alibaba Released 2025-04 Price $0.18 / $0.7 Length 131.1K | ||||
| 34 | NVIDIA-Nemotron-Nano-9B-v2-Japanese | NVIDIA | Rating 50.1 | — | — | — | — | — | NVIDIA Released — Price — Length — | ||
| 35 | Qwen3 235B A22B (instruct) | Alibaba | Rating 49.4 | — | — | 128K | Alibaba Released 2025-07 Price — Length 128K | ||||
| 36 | QwQ Bakeneko 32B | rinna | Rating 48.3 | — | — | — | — | — | rinna Released — Price — Length — | ||
| 37 | Qwen3 4B | Alibaba | Rating 48.2 | — | — | — | Alibaba Released 2025-04 Price — Length — | ||||
| 38 | Qwen3-Swallow-30B-A3B-CPT-v0.2 | Swallow (Science Tokyo) | Rating 48.1 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 39–40 | DeepSeek-R1-Distill-Qwen-32B-Japanese | CyberAgent | Rating 47.3 | — | — | — | — | — | CyberAgent Released — Price — Length — | ||
| 39–40 | Qwen3.5 9B | Alibaba | Rating 47.3 | — | — | 262K | Alibaba Released 2026-02 Price — Length 262K | ||||
| 41 | Llama 3.1 Nemotron Nano 8B (v1) | NVIDIA | Rating 46.7 | — | — | — | — | — | NVIDIA Released — Price — Length — | ||
| 42 | OLMo 3 7B Think | Ai2 | Rating 46.6 | — | — | — | — | — | Ai2 Released — Price — Length — | ||
| 43 | Gemma 4 E2B | Rating 42.9 | — | — | 131.1K | — | — | Google Released — Price — Length 131.1K | |||
| 44 | Qwen3-Swallow-8B-SFT-v0.2 | Swallow (Science Tokyo) | Rating 39.5 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 45 | GPT-4.1 | OpenAI | Rating 37.1 | $2 | $8 | 1.05M | OpenAI Released 2025-04 Price $2 / $8 Length 1.05M | ||||
| 46 | Qwen3.5 4B | Alibaba | Rating 36.5 | — | — | 262.1K | Alibaba Released 2026-02 Price — Length 262.1K | ||||
| 47 | Qwen3-Swallow-8B-CPT-v0.2 | Swallow (Science Tokyo) | Rating 34.2 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 48 | ELYZA-Thinking-1.0-Qwen-32B | ELYZA | Rating 32.3 | — | — | — | — | — | ELYZA Released — Price — Length — | ||
| 49 | Llama 4 Scout | Meta | Rating 31.1 | — | — | 128K | Meta Released 2025-04 Price — Length 128K | ||||
| 50 | Gemma 3 27B | Rating 30.1 | — | — | 128K | Google Released 2025-03 Price — Length 128K | |||||
| 51 | Qwen3 1.7B | Alibaba | Rating 29.7 | — | — | — | Alibaba Released 2025-04 Price — Length — | ||||
| 52 | LLM-jp-4 32B A3B | LLM-jp | Rating 29.3 | — | — | — | — | — | LLM-jp Released — Price — Length — | ||
| 53 | Llama 3.3 70B (instruct) | Meta | Rating 27.9 | — | — | 131.1K | Meta Released 2024-12 Price — Length 131.1K | ||||
| 54 | ELYZA-Shortcut-1.0-Qwen-32B | ELYZA | Rating 27.6 | — | — | — | — | — | ELYZA Released — Price — Length — | ||
| 55 | Gemma 3 12B | Rating 26.0 | — | — | 131K | Google Released 2025-03 Price — Length 131K | |||||
| 56 | LLM-jp-4 8B | LLM-jp | Rating 25.9 | — | — | — | — | — | LLM-jp Released — Price — Length — | ||
| 57 | GPT-4o (2024-08) | OpenAI | Rating 25.3 | $2.5 | $10 | 128K | OpenAI Released 2024-08 Price $2.5 / $10 Length 128K | ||||
| 58 | Llama 3.3 Swallow 70B (instruct, v0.4) | Swallow (Science Tokyo) | Rating 23.9 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 59 | Gemma 3 4B | Rating 17.7 | — | — | 131K | Google Released 2025-03 Price — Length 131K | |||||
| 60 | Llama 3.1 8B (instruct) | Meta | Rating 15.8 | — | — | 128K | Meta Released 2024-07 Price — Length 128K | ||||
| 61 | Qwen3 0.6B | Alibaba | Rating 14.8 | — | — | — | Alibaba Released 2025-04 Price — Length — | ||||
| 62 | Qwen3.5 2B | Alibaba | Rating 13.2 | — | — | 32.8K | Alibaba Released 2026-02 Price — Length 32.8K | ||||
| 63–64 | LLM-jp-3.1 13B (instruct4) | LLM-jp | Rating 11.2 | — | — | — | — | — | LLM-jp Released — Price — Length — | ||
| 63–64 | Sarashina2.2 3B (instruct, v0.1) | SB Intuitions | Rating 11.2 | — | — | — | — | — | SB Intuitions Released — Price — Length — | ||
| 65 | Llama 3.1 Swallow 8B (instruct, v0.5) | Swallow (Science Tokyo) | Rating 9.1 | — | — | — | — | — | Swallow (Science Tokyo) Released — Price — Length — | ||
| 66 | LLM-jp-3.1 1.8B (instruct4) | LLM-jp | Rating 5.1 | — | — | — | — | — | LLM-jp Released — Price — Length — | ||
| 67 | Qwen3.5 0.8B | Alibaba | Rating 3.3 | — | — | 32.8K | Alibaba Released 2026-02 Price — Length 32.8K | ||||
| 68 | Gemma 3 1B | Rating 2.7 | — | — | — | Google Released 2025-03 Price — Length — |
How to read this page
- Problems are chosen by release date to avoid ones used in training. The value is the share that pass.
- The accuracy is the share of problems solved. A gap of 1 point is 1 question out of 100.
- In the Supports column the icons are, from left: can use tools / can read images / can answer in a fixed format (JSON); faded means not supported or unknown.
- Open-weights models have their contents (the weights) published, so you can also run them on your own computer or server. Models without the open-weights mark are normally used through the developer's own services (apps or API); for some models the weights status is unknown.
- Names such as ChatGPT next to a model are the consumer services its developer offers. Check on the service itself whether that model is available there.
Data: Arena, Epoch AI, Swallow LLM team (CC BY 4.0), Models.dev (MIT), updated 2026-10-24, data sources