AI coding model comparison
📅 Data snapshot: November 2026
| Model | Family | Copilot | $/task | LiveBench 2.0 | Arena Code | SWE-bench |
|---|---|---|---|---|---|---|
| Claude Fable 5.1 | Anthropic | ✓ | $1.00 | 85.7 | 1537 | not tested |
| GPT-6 Astra | OpenAI | ✓ | $1.00 | 85.6 | 1542 | not tested |
| Claude Opus 5.5 | Anthropic | ✓ | $0.40 | 85.1 | 1551 | not tested |
| GPT-6.1 Sol | OpenAI | ✓ | $0.20 | 84.1 | 1541 | not tested |
| Claude Sonnet 5.5 | Anthropic | ✓ | $0.20 | 80.0 | 1529 | not tested |
| Gemini 4 Argon | ✓ | $0.20‡ | 79.3 | 1550 | not tested | |
| GPT-6.1 Terra | OpenAI | ✓ | $0.10 | 77.8 | not tested | not tested |
| Muse Wonder 1.0 | Meta | - | - | 74.2 | 1545 | not tested |
| DeepSeek V4.1 Flash | DeepSeek | - | $0.03* | 72.9 | 1523 | not tested |
| Kimi K3.1 Pro | Moonshot | - | - | 71.3 | not tested | not tested |
| Grok 4.7 | xAI | ✓ | $0.16 | 70.1 | 1494 | not tested |
| Claude Haiku 5.5 | Anthropic | ✓ | $0.01 | 69.8 | 1489 | not tested |
| MiMo V2.6 Pro | Xiaomi | - | - | 68.5 | 1538 | not tested |
| GPT-5.6 Terra | OpenAI | ✓ | $0.22 | 67.8 | 1517 | not tested |
| Grok 4.6 | xAI | ✓ | $0.16 | 67.8 | 1509 | not tested |
| MiniMax M3.1 Flash | Minimax | - | - | 66.9 | not tested | not tested |
| GPT-6 Luna | OpenAI | ✓ | $0.01 | 64.6 | 1506 | not tested |
| Kimi K3 | Moonshot | ✓ | - | 64.6 | 1540 | not tested |
| Muse Spark 1.3 | Meta | - | - | 63.0 | 1534 | not tested |
| GLM-5.3 Flash | Zhipu | - | - | 62.1 | 1526 | not tested |
| Qwen3.8 Max | Alibaba | - | - | 61.6 | 1525 | not tested |
| Gemini 3.8 Flash | ✓ | $0.075† | 59.2 | 1530 | not tested | |
| Qwen3.8 27B | Alibaba | - | - | 58.4 | 1498 | not tested |
| Claude Fable 5 | Anthropic | ✓ | $1.00 | not tested | 1550 | not tested |
| Claude Opus 5 | Anthropic | ✓ | $0.50 | not tested | 1534 | not tested |
| Claude Sonnet 5 | Anthropic | ✓ | $0.20 | not tested | 1520 | not tested |
| Claude Opus 4.8 | Anthropic | ✓ | $0.50 | not tested | 1534 | not tested |
| Claude Opus 4.7 | Anthropic | - | $0.50 | not tested | 1551 | not tested |
| Claude Opus 4.6 | Anthropic | - | $0.50 | not tested | 1548 | 75.6% |
| Claude Opus 4.5 | Anthropic | - | $0.50 | not tested | 1530 | 76.8% |
| Claude Sonnet 4.6 | Anthropic | ✓ | $0.30 | not tested | 1528 | not tested |
| Claude Sonnet 4.5 | Anthropic | - | $0.30 | not tested | 1519 | 71.4% |
| Claude Haiku 4.5 | Anthropic | ✓ | $0.10 | not tested | 1482 | 66.6% |
| GPT-6 Sol | OpenAI | ✓ | $0.20 | not tested | 1519 | not tested |
| GPT-5.6 Sol | OpenAI | ✓ | $0.40‡ | not tested | 1533 | not tested |
| GPT-5.6 Luna | OpenAI | ✓ | $0.02 | not tested | 1502 | not tested |
| GPT-5.5 | OpenAI | - | $0.55 | not tested | 1519 | not tested |
| GPT-5.4 | OpenAI | - | $0.28 | not tested | 1520 | not tested |
| GPT-5.4 mini | OpenAI | - | $0.08 | not tested | 1495 | not tested |
| GPT-5.4 nano | OpenAI | ✓ | $0.02 | not tested | 1460 | not tested |
| GPT-5.2 | OpenAI | - | $0.23 | not tested | 1489 | 72.8% |
| GPT-5 mini | OpenAI | - | $0.03 | not tested | 1432 | 56.2% |
| Gemini 3.6 Flash | - | $0.075† | not tested | 1518 | not tested | |
| Gemini 3.1 Pro | - | $0.22 | not tested | 1521 | not tested | |
| Gemini 3.5 Flash-Lite | - | $0.04 | not tested | 1502 | not tested | |
| Gemini 3 Flash | - | $0.06 | not tested | 1505 | 75.8% | |
| Gemini 2.5 Pro (retiring Dec 1) | - | $0.16 | not tested | 1464 | 53.6% | |
| Gemini 2.5 Flash (retiring Dec 1) | - | $0.04 | not tested | 1424 | 28.7% | |
| Grok 4.5 | xAI | ✓ | $0.16 | not tested | 1514 | not tested |
| DeepSeek V4 Pro 0813 | DeepSeek | - | $0.106* | not tested | 1505 | not tested |
| Muse Spark 1.2 | Meta | - | - | not tested | 1543 | not tested |
| GLM-5.3 | Zhipu | - | - | not tested | 1520 | not tested |
| GLM-5.2 | Zhipu | - | - | not tested | 1514 | not tested |
| GLM-5 | Zhipu | - | $0.05 | not tested | 1498 | 72.8% |
| GLM-4.7 | Zhipu | - | $0.05 | not tested | 1484 | not tested |
| Kimi K2.5 | Moonshot | - | - | not tested | 1504 | 70.8% |
| MiniMax M3 | Minimax | - | - | not tested | 1495 | not tested |
| MiniMax M2.5 | Minimax | - | $0.07 | not tested | 1446 | 75.8% |
Column guide
| Column | What it means |
|---|---|
| Copilot | Available in GitHub Copilot (✓ = listed, - = not listed). Copilot usage is billed in AI credits based on tokens used. |
| $/task | Estimated direct-API cost for 50K input + 10K output tokens; it is not a Copilot bill estimate. |
| LiveBench 2.0 | Weighted overall score (0-100) across seven suites: long agentic work, coding, design, browser use, data analysis, research and reasoning. Release 2026-10-25 (source). Not comparable with the old LiveBench 1 scores this page showed until October. |
| Arena Code | Rating from blind human votes on coding prompts, with Arena’s default style control. Published October 28, 2026 (source). Where Arena lists several effort settings for a model, the highest-rated one is shown; hover a score to see which, and how many votes it has. Current models sit between about 1490 and 1550, and the 95% confidence intervals are roughly ±6 to ±18 points, so many neighbouring models are statistically tied. |
| SWE-bench | % of 500 real GitHub issues fixed in the SWE-bench Verified standardized runs (source). Most runs date from February 2026; none of the models released since then has a run. |
DeepSeek V4.1 Flash and V4 Pro have peak and off-peak rates; this estimate uses peak pricing. Arena’s DeepSeek V4.1 Flash score is for the September 10 build, LiveBench’s for the October 17 build. †Gemini 3.6/3.8 Flash promotional API pricing runs through Dec 31, 2026; after that it doubles to $0.15/task. ‡Promotional pricing until Nov 30, 2026: Gemini 4 Argon then rises to $0.40/task; OpenAI has not published GPT-5.6 Sol’s rate after the promotion. Claude Haiku 5.5’s $0.01 applies to prompts up to 100K tokens. Gemini 2.5 Pro and 2.5 Flash are deprecated; from Dec 1, 2026 Google routes their requests to Gemini 3.8 Flash and 3.5 Flash-Lite.
Aider’s polyglot scores are no longer in this table: its leaderboard hasn’t added a model since October 2025. The archived results are on the benchmarks page, along with ProgramBench and the LiveBench per-suite scores.
API pricing: Anthropic · OpenAI · Google · DeepSeek · xAI · Zhipu (GLM)