# AgentLeaderboards — full leaderboard (markdown mirror)

Generated: 2026-09-12T05:44:58.492Z · https://agentleaderboards.com · JSON: /api/v1/leaderboard.json

Policy: every metric traces to a public source; missing data is "—", never estimated.

## Frontier models (source: OpenRouter catalog, retrieved 2026-09-12)

| Model | Provider | Released | Context | Input $/1M | Output $/1M | Tool calling |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | DeepSeek | 2026-09-10 | 1.048576M | $0.15 | $0.60 | yes |
| GPT-6 Astra | OpenAI | 2026-09-04 | 1.05M | $10.00 | $50.00 | yes |
| GPT-6 Astra Pro | OpenAI | 2026-09-04 | 1.05M | $10.00 | $50.00 | yes |
| Qwen3.8 Max (0902) | Qwen (Alibaba) | 2026-09-03 | 1M | $2.00 | $6.00 | yes |
| Gemini 3.8 Flash | Google | 2026-09-02 | 1.048576M | $0.75 | $3.75 | yes |
| Claude Fable 5.1 | Anthropic | 2026-09-01 | 1M | $10.00 | $50.00 | yes |
| Qwen3.8 Flash | Qwen (Alibaba) | 2026-08-26 | 1M | $0.15 | $0.47 | yes |
| GLM 5.3 Flash | Z.ai (Zhipu) | 2026-08-26 | 1.31072M | $0.15 | $0.50 | yes |
| DeepSeek V4 Flash Vision Exp | DeepSeek | 2026-08-21 | 1.048576M | $0.22 | $0.66 | yes |
| GLM 5.3 | Z.ai (Zhipu) | 2026-08-18 | 1.31072M | $1.40 | $4.40 | yes |
| Qwen3.8 27B | Qwen (Alibaba) | 2026-08-14 | 1M | $0.21 | $2.55 | yes |
| Gemini 3.7 Flash | Google | 2026-08-13 | 1.048576M | $0.75 | $3.75 | yes |
| DeepSeek V4 Pro 0813 | DeepSeek | 2026-08-12 | 1.048576M | $0.58 | $1.73 | yes |
| Qwen3.8 2.4T A95B | Qwen (Alibaba) | 2026-08-12 | 1.048576M | $2.00 | $6.00 | yes |
| Grok 4.6 | xAI | 2026-08-12 | 500K | $2.00 | $6.00 | yes |
| DeepSeek V4 Flash 0731 | DeepSeek | 2026-07-31 | 1.31072M | $0.04 | $0.08 | yes |
| Qwen3.7 Flash | Qwen (Alibaba) | 2026-07-27 | 1M | $0.03 | $0.13 | yes |
| Claude Opus 5 | Anthropic | 2026-07-24 | 1M | $5.00 | $25.00 | yes |
| Gemini 3.6 Flash | Google | 2026-07-21 | 1.048576M | $0.75 | $3.75 | yes |
| Gemini 3.5 Flash Lite | Google | 2026-07-21 | 1.048576M | $0.30 | $2.50 | yes |
| Kimi K3 | Moonshot AI | 2026-07-16 | 1.048576M | $2.30 | $11.55 | yes |
| GPT-5.6 Luna Pro | OpenAI | 2026-07-09 | 1.05M | $0.20 | $1.20 | yes |
| GPT-5.6 Luna | OpenAI | 2026-07-09 | 1.05M | $0.20 | $1.20 | yes |
| GPT-5.6 Terra Pro | OpenAI | 2026-07-09 | 1.05M | $2.00 | $12.00 | yes |
| GPT-5.6 Terra | OpenAI | 2026-07-09 | 1.05M | $2.00 | $12.00 | yes |
| GPT-5.6 Sol Pro | OpenAI | 2026-07-09 | 1.05M | $2.00 | $10.00 | yes |
| GPT-5.6 Sol | OpenAI | 2026-07-09 | 1.05M | $2.00 | $10.00 | yes |
| Grok 4.5 | xAI | 2026-07-08 | 500K | $2.00 | $6.00 | yes |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | Google | 2026-06-30 | 66K | $0.25 | $1.50 | no |
| Claude Sonnet 5 | Anthropic | 2026-06-30 | 1M | $2.00 | $10.00 | yes |
| Nano Banana 2 (Gemini 3.1 Flash Image) | Google | 2026-06-18 | 131K | $0.50 | $3.00 | no |
| Nano Banana Pro (Gemini 3 Pro Image) | Google | 2026-06-18 | 131K | $2.00 | $12.00 | yes |
| GLM 5.2 | Z.ai (Zhipu) | 2026-06-16 | 1.048576M | $0.60 | $2.00 | yes |
| Kimi K2.7 Code | Moonshot AI | 2026-06-12 | 262K | $0.71 | $3.50 | yes |
| Claude Fable 5 | Anthropic | 2026-06-09 | 1M | $10.00 | $50.00 | yes |
| Qwen3.7 Plus | Qwen (Alibaba) | 2026-06-03 | 1M | $0.32 | $1.28 | yes |
| MiniMax M3 | MiniMax | 2026-05-31 | 1.048576M | $0.30 | $1.20 | yes |
| Claude Opus 4.8 | Anthropic | 2026-05-27 | 1M | $5.00 | $25.00 | yes |
| Qwen3.7 Max | Qwen (Alibaba) | 2026-05-21 | 1M | $1.48 | $4.42 | yes |
| Grok Build 0.1 | xAI | 2026-05-20 | 256K | $1.00 | $2.00 | yes |
| Gemini 3.5 Flash | Google | 2026-05-19 | 1.048576M | $1.50 | $9.00 | yes |
| Grok 4.3 | xAI | 2026-04-30 | 1M | $1.25 | $2.50 | yes |
| Mistral Medium 3.5 | Mistral | 2026-04-30 | 262K | $1.50 | $7.50 | yes |
| Qwen3.5 Plus 2026-04-20 | Qwen (Alibaba) | 2026-04-27 | 1M | $0.30 | $1.80 | yes |
| DeepSeek V4 Pro 0423 | DeepSeek | 2026-04-24 | 1.048576M | $0.82 | $1.64 | yes |
| DeepSeek V4 Flash 0423 | DeepSeek | 2026-04-24 | 1.048576M | $0.07 | $0.13 | yes |
| Kimi K2.6 | Moonshot AI | 2026-04-20 | 262K | $0.95 | $4.00 | yes |
| Claude Opus 4.7 | Anthropic | 2026-04-16 | 1M | $5.00 | $25.00 | yes |
| GLM 5.1 | Z.ai (Zhipu) | 2026-04-07 | 205K | $0.97 | $3.04 | yes |
| GLM 5V Turbo | Z.ai (Zhipu) | 2026-04-01 | 203K | $1.20 | $4.00 | yes |
| Grok 4.20 Multi-Agent | xAI | 2026-03-31 | 2M | $1.25 | $2.50 | no |
| Grok 4.20 | xAI | 2026-03-31 | 2M | $1.25 | $2.50 | yes |
| MiniMax M2.7 | MiniMax | 2026-03-18 | 205K | $0.30 | $1.20 | yes |
| Mistral Small 4 | Mistral | 2026-03-16 | 262K | $0.15 | $0.60 | yes |
| GLM 5 Turbo | Z.ai (Zhipu) | 2026-03-15 | 203K | $1.20 | $4.00 | yes |
| Claude Sonnet 4.6 | Anthropic | 2026-02-17 | 1M | $3.00 | $15.00 | yes |
| MiniMax M2.5 | MiniMax | 2026-02-12 | 205K | $0.30 | $1.20 | yes |
| GLM 5 | Z.ai (Zhipu) | 2026-02-11 | 205K | $0.60 | $1.92 | yes |
| Claude Opus 4.6 | Anthropic | 2026-02-04 | 1M | $5.00 | $25.00 | yes |
| Kimi K2.5 | Moonshot AI | 2026-01-27 | 262K | $0.45 | $2.25 | yes |
| MiniMax M2-her | MiniMax | 2026-01-23 | 66K | $0.30 | $1.20 | no |
| GLM 4.7 Flash | Z.ai (Zhipu) | 2026-01-19 | 200K | $0.06 | $0.40 | yes |
| MiniMax M2.1 | MiniMax | 2025-12-23 | 205K | $0.30 | $1.20 | yes |
| Devstral 2 2512 | Mistral | 2025-12-09 | 262K | $0.40 | $2.00 | yes |
| Ministral 3 14B 2512 | Mistral | 2025-12-02 | 262K | $0.20 | $0.20 | yes |
| Ministral 3 8B 2512 | Mistral | 2025-12-02 | 262K | $0.15 | $0.15 | yes |
| Ministral 3 3B 2512 | Mistral | 2025-12-02 | 131K | $0.10 | $0.10 | yes |
| DeepSeek V3.2 | DeepSeek | 2025-12-01 | 164K | $0.27 | $0.40 | yes |
| Mistral Large 3 2512 | Mistral | 2025-12-01 | 262K | $0.50 | $1.50 | yes |
| Kimi K2 Thinking | Moonshot AI | 2025-11-06 | 262K | $0.60 | $2.50 | yes |
| Voxtral Small 24B 2507 | Mistral | 2025-10-30 | 33K | $0.10 | $0.30 | yes |
| MiniMax M2 | MiniMax | 2025-10-23 | 205K | $0.26 | $1.02 | yes |

## Agent frameworks (source: GitHub API, retrieved 2026-09-12)

| Framework | Category | Language | Stars | Forks | Last push | License |
|---|---|---|---|---|---|---|
| OpenClaw | personal-assistant | TypeScript | 389,475 | 81,872 | 2026-09-12 | Other |
| Hermes Agent | personal-assistant | Python | 244,671 | 50,729 | 2026-09-12 | MIT |
| Claude Code | coding-agent | Python | 144,799 | 23,117 | 2026-09-11 | — |
| Codex CLI | coding-agent | Rust | 123,462 | 19,006 | 2026-09-12 | Apache-2.0 |
| Gemini CLI | coding-agent | TypeScript | 106,930 | 14,558 | 2026-09-12 | Apache-2.0 |
| OpenHands | coding-agent | TypeScript | 87,577 | 11,469 | 2026-09-12 | MIT |
| Cline | coding-agent | TypeScript | 67,863 | 7,331 | 2026-09-12 | Apache-2.0 |
| AutoGen | orchestration-sdk | Python | 60,941 | 9,206 | 2026-04-15 | CC-BY-4.0 |
| CrewAI | orchestration-sdk | Python | 58,387 | 8,408 | 2026-09-11 | MIT |
| aider | coding-agent | Python | 48,913 | 4,945 | 2026-05-22 | Apache-2.0 |
| LangGraph | orchestration-sdk | Python | 41,492 | 7,011 | 2026-09-11 | MIT |
| gcrab *(our project)* | personal-assistant | Go | 0 | 0 | 2026-09-10 | MIT |

Disclosure: gcrab is built by this site's operators; its repo is not yet public so GitHub columns are empty.

## SWE-bench Verified — top 20 (source: swebench.com, retrieved 2026-09-12)

| # | Agent + model | Resolved | Date | Status |
|---|---|---|---|---|
| 1 | Sonar Foundation Agent + Claude 4.5 Opus | 79.2% | 2025-12-05 | self-reported |
| 2 | live-SWE-agent + Claude 4.5 Opus medium (20251101) | 79.2% | 2025-12-15 | self-reported |
| 3 | TRAE + Doubao-Seed-Code | 78.8% | 2025-09-28 | self-reported |
| 4 | live-SWE-agent + Gemini 3 Pro Preview (2025-11-18) | 77.4% | 2025-11-20 | self-reported |
| 5 | EPAM AI/Run Developer Agent v20250719 + Claude 4 Sonnet | 76.8% | 2025-08-04 | self-reported |
| 6 | Atlassian Rovo Dev (2025-09-02) | 76.8% | 2025-09-02 | self-reported |
| 7 | Claude 4.5 Opus (high) | 76.8% | 2026-02-17 | self-reported |
| 8 | ACoder | 76.4% | 2025-08-19 | self-reported |
| 9 | Gemini 3 Flash (high) | 75.8% | 2026-02-17 | self-reported |
| 10 | MiniMax M2.5 (high) | 75.8% | 2026-02-17 | self-reported |
| 11 | Warp | 75.6% | 2025-09-01 | self-reported |
| 12 | Claude 4.6 Opus | 75.6% | 2026-02-17 | self-reported |
| 13 | TRAE + Claude Sonnet 4 + Opus 4 + Sonnet 3.7 + Gemini 2.5 Pro | 75.2% | 2025-06-12 | self-reported |
| 14 | Harness AI | 74.8% | 2025-07-31 | self-reported |
| 15 | Sonar Foundation Agent + Claude 4.5 Sonnet | 74.8% | 2025-11-03 | self-reported |
| 16 | Lingxi-v1.5_claude-4-sonnet-20250514 | 74.6% | 2025-07-20 | self-reported |
| 17 | JoyCode + Claude 4 Sonnet + GPT-4.1 | 74.6% | 2025-09-15 | self-reported |
| 18 | Refact.ai Agent + Claude 4 Sonnet + o4-mini | 74.4% | 2025-06-03 | self-reported |
| 19 | Prometheus-v1.2.1 + GPT-5 | 74.4% | 2025-10-15 | self-reported |
| 20 | Claude 4.5 Opus (20251101) (medium) | 74.4% | 2025-11-24 | checked |