MODEL LEADERBOARDS
Leaderboard
Ranks come verbatim from each evaluator's own official board, synced on a schedule. The rulers differ (Arena is human-preference Elo, Terminal-Bench a task success rate, SWE-bench an issue resolve rate), so a score is only comparable within its own board — a cross-board composite would look comparable without being so. This page gives three things: who is on top, by how much, and when the score was measured.
- Boards
- 12
- Ranked entries
- 481
- Evaluators
- 6
Last sync Oct 19, 2026Top 25 per board; the footnote links to the full official board.
Embodied AI
2 boards · 45 entriesRoboDojo Simulation Leaderboard
robodojo-benchmark.comranked by: Official composite scoreUnified embodied-policy eval: 42 sim tasks across generalization, precision, long-horizon, memory and open-ended dims.
| # | Model | Gen-Std | Gen-Rand | Precision | Long-Horizon | Memory | Open-Ended | Average |
|---|---|---|---|---|---|---|---|---|
| 1 | DM0.5Dexmal | 23.5 | 8.1 | 24.8 | 33.7 | 47.7 | 2.4 | 24.9 |
| 2 | GalaxeaVLA (G0.5)Galaxea AI | 26.7 | 11.2 | 28.3 | 44.1 | 8.6 | 1.7 | 20.2 |
| 3 | Xiaomi-Robotics-1Xiaomi Robotics | 35.7 | 11.4 | 26.7 | 38.4 | 7.8 | 3.9 | 20.1 |
| 4 | Hy-Embodied-0.5-VLATencent Robotics X | 22 | 1.6 | 13.8 | 25.7 | 13.4 | 0.7 | 13.1 |
| 5 | Spatial ForcingOpenHelix Robotics | 21.3 | 7 | 17.3 | 23.3 | 5.4 | 1.8 | 12.4 |
| 6 | Pi-05RoboDojo Team | 20.9 | 5.8 | 12.4 | 23.5 | 5.8 | 2 | 11.4 |
| 7 | InternVLA-A1.5InternVLA Team | 16.8 | 3.9 | 15.2 | 23.8 | 4.9 | 1.4 | 11.2 |
| 8 | VLActStarVLA Team | 16.3 | 2.7 | 20.6 | 20.1 | 0.7 | 2.4 | 10.7 |
| 9 | X-VLARoboDojo Team | 17.9 | 3 | 18.3 | 16.5 | 4.8 | 0.6 | 10.1 |
| 10 | X-WAMX-WAM Team | 11.2 | 3.5 | 6.7 | 17.5 | 6.3 | 0.6 | 7.7 |
| 11 | Xiaomi-Robotics-0RoboDojo Team | 13.8 | 1.1 | 8.4 | 13.5 | 5.1 | 0.2 | 6.9 |
| 12 | StarVLARoboDojo Team | 7.5 | 0.3 | 9.9 | 14.2 | 3.3 | 0.7 | 6.4 |
| 13 | GigaWorld-Policy-0RoboDojo Team | 10.3 | 0.4 | 6.2 | 15.5 | 3.5 | 0.5 | 6.2 |
| 14 | GalaxeaVLA (G0)RoboDojo Team | 8.7 | 0.4 | 8.1 | 12.6 | 3.2 | 0.7 | 5.8 |
| 15 | LingBot-VLARoboDojo Team | 10.9 | 2.6 | 5.3 | 10.9 | 3.8 | 0.7 | 5.5 |
| 16 | EventVLASJTU ScaleLab | 6.7 | 1.2 | 10.1 | 5.1 | 4.9 | 0.8 | 5 |
| 17 | AHA-WAMSJTU ScaleLab | 10.3 | 1.3 | 5.9 | 8.6 | 3 | 0.9 | 4.8 |
| 18 | ABot-M0RoboDojo Team | 9.2 | 2.3 | 5.5 | 4 | 2.4 | 0.7 | 3.7 |
| 19 | Fast-WAMRoboDojo Team | 4.3 | 0.3 | 2 | 9.1 | 3.6 | 0.4 | 3.5 |
| 20 | Pi-0RoboDojo Team | 7.2 | 0.7 | 3.6 | 6.2 | 3.5 | 0.3 | 3.5 |
| 21 | GROOT-N1.7RoboDojo Team | 4 | 0.4 | 2.5 | 8.3 | 1.1 | 0.2 | 2.9 |
| 22 | InternVLA-A1RoboDojo Team | 5.2 | 0.5 | 3 | 4.8 | 1.6 | 0.2 | 2.5 |
| 23 | SmolVLA (Single Task)RoboDojo Team | 3.3 | 0.1 | 2.9 | 1.2 | 3.4 | 0 | 1.8 |
| 24 | LDA-1BRoboDojo Team | 1.4 | 0.2 | 3.2 | 1.9 | 2.1 | 0 | 1.6 |
| 25 | MolmoAct2RoboDojo Team | 0.7 | 0 | 0.5 | 2.3 | 1 | 0.9 | 1 |
RoboDojo Real-World Leaderboard
robodojo-benchmark.comranked by: Official composite scoreReal-robot embodied eval: 18 tasks on ARX X5, Piper and Piper X.
| # | Model | ARX X5 | Piper | Piper X | Average |
|---|---|---|---|---|---|
| 1 | Pi-05RoboDojo Team | 27.7 | 32 | 9.1 | 22.9 |
| 2 | InternVLA-A1RoboDojo Team | 10 | 23.2 | 2.7 | 12 |
| 3 | GalaxeaVLA (G0)RoboDojo Team | 3.4 | 22 | 1.7 | 9 |
| 4 | Xiaomi-Robotics-0RoboDojo Team | 15 | 7.6 | 1.2 | 7.9 |
| 5 | X-VLARoboDojo Team | 6.8 | 15.9 | 0.1 | 7.6 |
| 6 | GROOT-N1.7RoboDojo Team | 9.3 | 6.8 | 1.4 | 5.9 |
| 7 | Pi-0RoboDojo Team | 8.1 | 9 | 0.3 | 5.8 |
| 8 | StarVLARoboDojo Team | 0 | 12 | 0.5 | 4.1 |
| 9 | Spirit v1.5RoboDojo Team | 0 | 4 | 0.7 | 1.6 |
| 10 | DM0RoboDojo Team | 0 | 0 | 0 | 0 |
Large Language Models
2 boards · 100 entriesArtificial Analysis Intelligence Index
artificialanalysis.airanked by: Official intelligence index (higher is better)Artificial Analysis' own composite intelligence index: knowledge, reasoning and agentic evaluations folded into a single scale — the most widely cited cross-vendor measure of absolute capability. Different reasoning efforts of the same model are listed separately, as the source does.
| # | Model | Intelligence Index | Price in $/M | Price out $/M | Notes |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 (max with fallback)Anthropic | 57.62 | $4 | $20 | 1M · 2026-09-22 |
| 2 | Claude Sonnet 5.5 (max with fallback)Anthropic | 56 | $2 | $10 | 1M · 2026-09-28 |
| 3 | Claude Opus 5.5 (xhigh with fallback)Anthropic | 55.99 | $4 | $20 | 1M · 2026-09-22 |
| 4 | Muse Wonder Full (max)Meta | 55.8 | — | — | 1M · 2026-10-12 |
| 5 | Claude Opus 5.5 (high with fallback)Anthropic | 53.58 | $4 | $20 | 1M · 2026-09-22 |
| 6 | Claude Fable 5.1 (max with fallback)Anthropic | 53.35 | $10 | $50 | 1M · 2026-09-01 |
| 7 | Claude Fable 5.1 (xhigh with fallback)Anthropic | 53.2 | $10 | $50 | 1M · 2026-09-01 |
| 8 | GPT-6 Astra (max)OpenAI | 52.67 | $10 | $50 | 1M · 2026-09-03 |
| 9 | Gemini 4 Argon (high)Google | 52.56 | $2 | $10 | 1M · 2026-09-30 |
| 10 | Muse Wonder (max)Meta | 52.39 | $4 | $20 | 1.05M · 2026-10-12 |
| 11 | GPT-6 Astra (xhigh)OpenAI | 52.39 | $10 | $50 | 1M · 2026-09-03 |
| 12 | Claude Sonnet 5.5 (xhigh with fallback)Anthropic | 51.9 | $2 | $10 | 1M · 2026-09-28 |
| 13 | GPT-6.1 Sol (max)OpenAI | 51.83 | $2 | $10 | 1M · 2026-09-29 |
| 14 | Claude Opus 5.5 (medium with fallback)Anthropic | 51.24 | $4 | $20 | 1M · 2026-09-22 |
| 15 | Claude Fable 5.1 (high with fallback)Anthropic | 51.15 | $10 | $50 | 1M · 2026-09-01 |
| 16 | GPT-6.1 Sol (xhigh)OpenAI | 51.04 | $2 | $10 | 1M · 2026-09-29 |
| 17 | GPT-6 Astra (high)OpenAI | 50.92 | $10 | $50 | 1M · 2026-09-03 |
| 18 | GPT-6.1 Sol (high)OpenAI | 50.24 | $2 | $10 | 1M · 2026-09-29 |
| 19 | GPT-6 Astra (medium)OpenAI | 49.57 | $10 | $50 | 1M · 2026-09-03 |
| 20 | Claude Fable 5.1 (medium with fallback)Anthropic | 48.92 | $10 | $50 | 1M · 2026-09-01 |
| 21 | Muse Spark 1.3 (max)Meta | 48.09 | $1.25 | $4.25 | 1M · 2026-09-02 |
| 22 | GPT-6.1 Sol (medium)OpenAI | 47.78 | $2 | $10 | 1M · 2026-09-29 |
| 23 | Claude Fable 5.1 (low with fallback)Anthropic | 46.82 | $10 | $50 | 1M · 2026-09-01 |
| 24 | Claude Sonnet 5.5 (high with fallback)Anthropic | 46.75 | $2 | $10 | 1M · 2026-09-28 |
| 25 | Grok 4.7 (xhigh)SpaceXAI | 46.45 | $2 | $6 | 500k · 2026-09-21 |
Arena Text Chatbot Leaderboard
arena.airanked by: Arena preference score (higher is better)The largest ongoing human-preference blind eval: Arena (formerly LMArena) ranks models by anonymous real-user battle votes.
| # | Model | Arena score | Votes | Price in $/M | Price out $/M | Notes |
|---|---|---|---|---|---|---|
| 1 | Gemini 4 Argon (High)Google | 1524±9 | 4,904 | $2 | $10 | 1M |
| 2 | Muse Wonder (Max)Meta | 1509±11 | 3,247 | $4 | $20 | 1M |
| 3 | Claude Opus 5.5 (High)Anthropic | 1508±7 | 8,300 | $4 | $20 | 1M |
| 4 | Claude Fable 5 (High)Anthropic | 1504±4 | 42,004 | $10 | $50 | 1M |
| 5 | Claude Opus 4.6 (High)Anthropic | 1503±3 | 81,394 | $5 | $25 | 1M |
| 6 | Claude Fable 5.1 (Max)Anthropic | 1502±6 | 14,590 | $10 | $50 | 1M |
| 7 | Claude Opus 4.7 (High)Anthropic | 1501±4 | 65,116 | $5 | $25 | 1M |
| 8 | Claude Opus 4.6Anthropic | 1497±3 | 86,071 | $5 | $25 | 1M |
| 9 | Gemini 3.8 Flash (High)Google | 1496±5 | 37,454 | $0.75 | $3.75 | 1M |
| 10 | Muse Spark 1.3 (Max)Meta | 1494±6 | 17,561 | $1.25 | $4.25 | 1M |
| 11 | Claude Opus 4.7Anthropic | 1494±4 | 66,216 | $5 | $25 | 1M |
| 12 | Muse Spark 1.2 (xHigh)Meta | 1493±7 | 8,248 | $1.25 | $4.25 | N/A |
| 13 | Muse Spark 1.1Meta | 1490±4 | 42,810 | $1.25 | $4.25 | N/A |
| 14 | Claude Opus 5 (Max)Anthropic | 1490±5 | 32,495 | $5 | $25 | 1M |
| 15 | Claude Opus 5 (High)Anthropic | 1490±4 | 66,824 | $5 | $25 | 1M |
| 16 | Muse SparkMeta | 1489±6 | 14,150 | — | — | N/A |
| 17 | Gemini 3.7 Flash (High)Google | 1488±5 | 27,232 | $0.75 | $3.75 | 1M |
| 18 | Kimi K3 (Max)Moonshot | 1487±5 | 32,795 | — | — | N/A |
| 19 | Gemini 3.1 Pro PreviewGoogle | 1487±3 | 127,649 | $1 | $6 | 1M |
| 20 | Gemini 3 ProGoogle | 1485±4 | 42,072 | $2 | $12 | 1M |
| 21 | GPT-5.6 Sol (xHigh)OpenAI | 1485±4 | 40,442 | $4 | $20 | N/A |
| 22 | GPT-6.1 Sol (Max)OpenAI | 1484±8 | 6,320 | $2 | $10 | 1.1M |
| 23 | Gemini 3.6 Flash (High)Google | 1483±4 | 36,122 | $0.75 | $3.75 | 1M |
| 24 | Qwen3.8-MaxAlibaba | 1482±5 | 27,766 | $2 | $6 | 1M |
| 25 | Claude Opus 4.8 (High)Anthropic | 1481±4 | 64,100 | $5 | $25 | 1M |
Agents
2 boards · 85 entriesArena Agent Leaderboard
arena.airanked by: Net improvement in percentage pointsArena's agent eval: net improvement, confirmed success and praise-vs-complaint on real tool-use tasks.
| # | Model | Net improvement | Confirmed success | Praise vs complaint |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 (Max)Anthropic | 18.88% | 20.31% | 39.93% |
| 2 | GPT-6 Astra (Max)OpenAI | 14.13% | 12.06% | 31.14% |
| 3 | Claude Fable 5.1 (Max)Anthropic | 14.03% | 15.73% | 27.15% |
| 4 | GPT-6.1 Sol (Max)OpenAI | 13.6% | 13.77% | 31.75% |
| 5 | Gemini 4 Argon (High)Google | 13.23% | 14.17% | 30.56% |
| 6 | Claude Sonnet 5.5 (Max)Anthropic | 12.99% | 21.13% | 18.44% |
| 7 | GPT-6 Sol (Max)OpenAI | 10.31% | 8.98% | 20% |
| 8 | Claude Opus 5 (Max)Anthropic | 8.68% | 12.26% | 13.39% |
| 9 | Claude Fable 5 (High)Anthropic | 8.18% | 4.45% | 15.39% |
| 10 | GPT-5.6 Sol (xHigh)OpenAI | 7.08% | 2.76% | 14.23% |
| 11 | Muse Wonder (Max)Meta | 4.94% | 9.51% | 4.41% |
| 12 | Claude Sonnet 5 (High)Anthropic | 4.58% | 1.08% | 4.77% |
| 13 | MiMo-V2.6-ProXiaomi | 3.95% | 7.89% | 5.56% |
| 14 | Muse Spark 1.3 (Max)Meta | 3.82% | 5.51% | 4.32% |
| 15 | Gemini 3.8 Flash (High)Google | 3.75% | 4.25% | 4.45% |
| 16 | Grok 4.7 (xHigh)SpaceXAI | 3.21% | 6.84% | 2.95% |
| 17 | GPT-5.5 (xHigh)OpenAI | 3.14% | -2.51% | 6.43% |
| 18 | GPT-6 Luna (Max)OpenAI | 3.01% | 1.08% | 0.7% |
| 19 | DeepSeek-V4.1-Flash-20260910 (Max)DeepSeek | 2.74% | 7.01% | 3.2% |
| 20 | Hy4 previewTencent | 2.68% | 5.97% | 4.76% |
| 21 | MiMo-V2.6-FlashXiaomi | 2.6% | 7.73% | 2.92% |
| 22 | GLM-5.2 (Max)Z.ai | 2.26% | 3.25% | 6.52% |
| 23 | Kimi K3 (Max)Moonshot | 1.93% | 6.03% | 2.27% |
| 24 | GLM-5.3 (Max)Z.ai | 1.78% | 3.61% | 5.73% |
| 25 | Qwen3.8-MaxAlibaba | 1.76% | 4.45% | 1.66% |
Terminal-Bench 4.0
tbench.airanked by: Task success rate %Hard terminal-agent benchmark: success rate, cost and tokens on real shell/engineering tasks, maintained by the Laude Institute.
| # | Model | Accuracy % | pass@5 | Trials | Notes |
|---|---|---|---|---|---|
| 1 | Opus 5.5Anthropic · Claude Code | 64.9% | 78.8% | 330 | Claude Code · $4.7k · 2026-09-22 |
| 2 | Sonnet 5.5Anthropic · Claude Code | 61.8% | 77.3% | 330 | Claude Code · $7.3k · 2026-09-28 |
| 3 | GPT-6 AstraOpenAI · Codex | 58.2% | 71.2% | 330 | Codex · $3.3k · 2026-09-03 |
| 3 | GPT-6.1 SolOpenAI · Codex | 58.2% | 74.2% | 330 | Codex · $634.24 · 2026-09-29 |
| 5 | Fable 5.1Anthropic · Claude Code | 57.9% | 78.8% | 330 | Claude Code · $6.2k · 2026-09-01 |
| 5 | GPT-6 AstraOpenAI · Codex | 57.9% | 69.7% | 330 | Codex · $2.4k · 2026-09-03 |
| 5 | GPT-6 AstraOpenAI · Codex | 57.9% | 71.2% | 330 | Codex · $2.3k · 2026-09-03 |
| 5 | Fable 5.1Anthropic · Claude Code | 57.9% | 75.8% | 330 | Claude Code · $4.9k · 2026-09-01 |
| 9 | Fable 5.1Anthropic · Claude Code | 54.6% | 75.8% | 330 | Claude Code · $4.0k · 2026-09-01 |
| 10 | GPT-6 AstraOpenAI · Codex | 54.2% | 66.7% | 330 | Codex · $1.9k · 2026-09-03 |
| 11 | Fable 5.1Anthropic · Claude Code | 53.9% | 71.2% | 330 | Claude Code · $2.8k · 2026-09-01 |
| 11 | Opus 5Anthropic · Claude Code | 53.9% | 69.7% | 330 | Claude Code · $6.1k · 2026-07-24 |
| 13 | Opus 5Anthropic · Claude Code | 51.8% | 69.7% | 330 | Claude Code · $6.0k · 2026-07-24 |
| 14 | GPT-6 AstraOpenAI · Codex | 50.6% | 63.6% | 330 | Codex · $1.6k · 2026-09-03 |
| 15 | Opus 5Anthropic · Claude Code | 50.3% | 74.2% | 330 | Claude Code · $4.7k · 2026-07-24 |
| 16 | GPT-6 SolOpenAI · Codex | 49.4% | 66.7% | 330 | Codex · $1.5k · 2026-09-22 |
| 17 | Opus 5Anthropic · Claude Code | 44.9% | 69.7% | 330 | Claude Code · $3.2k · 2026-07-24 |
| 18 | Fable 5Anthropic · Claude Code | 44.6% | 68.2% | 330 | Claude Code · $7.3k · 2026-06-09 |
| 19 | Fable 5.1Anthropic · Claude Code | 43.3% | 65.1% | 330 | Claude Code · $2.4k · 2026-09-01 |
| 20 | GLM-5.3Z.ai · Claude Code | 41.8% | 57.6% | 330 | Claude Code · $2.7k · 2026-08-14 |
| 21 | Grok 4.7xAI · Grok Build | 37.6% | 60.6% | 330 | Grok Build · $3.68k (partial: 324/330) · 2026-09-21 |
| 22 | GPT-5.6 SolOpenAI · Codex | 37.3% | 60.6% | 330 | Codex · $2.5k · 2026-06-26 |
| 23 | GLM-5.3-FlashZ.ai · Claude Code | 35.8% | 56.1% | 330 | Claude Code · $2.9k · 2026-08-26 |
| 24 | Opus 5Anthropic · Claude Code | 34.9% | 62.1% | 330 | Claude Code · $2.4k · 2026-07-24 |
| 25 | Qwen3.8-Max-0902Alibaba · Claude Code | 27% | 53% | 330 | Claude Code · $4.6k · 2026-09-02 |
Code
1 boards · 49 entriesSWE-bench Verified
swe-bench.comranked by: Issue resolve rate %Real GitHub-issue repair benchmark (OpenAI-verified subset): end-to-end agent resolve rate, the hardest public signal for coding models.
| # | Model | Resolved % | Cost $ | Notes |
|---|---|---|---|---|
| 1 | Sonar Foundation Agent + Claude 4.5 OpusAnthropic | 79.2% | — | 2025-12-05 |
| 2 | live-SWE-agent + Claude 4.5 OpusAnthropic | 79.2% | — | 2025-12-15 |
| 3 | TRAE + Doubao-Seed-CodeByteDance | 78.8% | — | 2025-09-28 |
| 4 | live-SWE-agent + Gemini 3 Pro PreviewGoogle DeepMind | 77.4% | — | 2025-11-20 |
| 5 | EPAM AI/Run Developer Agent + Claude 4 SonnetAnthropic | 76.8% | — | 2025-08-04 |
| 6 | Atlassian Rovo Dev + MultipleAnthropic | 76.8% | — | 2025-09-02 |
| 7 | mini-SWE-agent + Claude 4.5 OpusAnthropic | 76.8% | $376.95 | 2026-02-17 |
| 8 | ACoder + MultipleAnthropic | 76.4% | — | 2025-08-19 |
| 9 | mini-SWE-agent + Gemini 3 FlashGoogle DeepMind | 75.8% | $177.98 | 2026-02-17 |
| 10 | mini-SWE-agent + MiniMax M2.5Minimax | 75.8% | $36.64 | 2026-02-17 |
| 11 | Warp + MultipleOpenAI | 75.6% | — | 2025-09-01 |
| 12 | mini-SWE-agent + Claude 4.6 OpusAnthropic | 75.6% | $275.76 | 2026-02-17 |
| 13 | TRAE + MultipleAnthropic | 75.2% | — | 2025-06-12 |
| 14 | Harness AI + Claude Sonnet 4Anthropic | 74.8% | — | 2025-07-31 |
| 15 | Sonar Foundation Agent + Claude 4.5 SonnetAnthropic | 74.8% | — | 2025-11-03 |
| 16 | Lingxi-v1.5 + Claude 4 SonnetAnthropic | 74.6% | — | 2025-07-20 |
| 17 | JoyCode + MultipleAnthropic | 74.6% | — | 2025-09-15 |
| 18 | Refact.ai Agent + MultipleAnthropic | 74.4% | — | 2025-06-03 |
| 19 | Prometheus-v1.2.1 + GPT-5OpenAI | 74.4% | — | 2025-10-15 |
| 20 | mini-SWE-agent + Claude 4.5 OpusAnthropic | 74.4% | $360.62 | 2025-11-24 |
| 21 | mini-SWE-agent + Gemini 3 Pro PreviewGoogle DeepMind | 74.2% | $229.98 | 2025-11-18 |
| 22 | Salesforce AI Research SAGE + MultipleAnthropic | 73.8% | — | 2025-11-03 |
| 23 | Tools + Claude 4 OpusAnthropic | 73.2% | — | 2025-05-22 |
| 24 | Salesforce AI Research SAGE + MultipleAnthropic | 73% | — | 2025-10-21 |
| 25 | mini-SWE-agent + GLM 5Z-AI | 72.8% | $267.19 | 2026-02-17 |
Image Generation
2 boards · 100 entriesArena Text-to-Image Leaderboard
arena.airanked by: Arena preference score (higher is better)Arena text-to-image preference board: blind pairwise votes on identical prompts; Elo-style score and vote count.
| # | Model | Arena score | Votes |
|---|---|---|---|
| 1 | GPT-Image-2.5 SunburstOpenAI | 1425±7prelim | 17,752 |
| 2 | GPT-Image-2.5 FlareOpenAI | 1398±7prelim | 16,889 |
| 3 | GPT-Image-2 (Medium)OpenAI | 1383±4 | 93,334 |
| 4 | Grok Imagine Image 2.0SpaceXAI | 1334±12prelim | 3,113 |
| 5 | MAI-Image-2.6Microsoft AI | 1332±5 | 25,091 |
| 6 | Gemini Nano Banana 2.1Google | 1328±9prelim | 5,310 |
| 7 | Reve 2.1Reve | 1302±8 | 8,249 |
| 8 | Grok Imagine Image 2.0 (20260801)SpaceXAI | 1294±6 | 14,483 |
| 9 | Muse ImageMeta | 1274±5 | 42,262 |
| 10 | Reve 2.0Reve | 1269±6 | 15,773 |
| 11 | Gemini 3.1 Flash Image (nano-banana-2, Web Search)Google | 1262±4 | 60,515 |
| 12 | Seedream 5.0 ProBytedance | 1255±4 | 94,181 |
| 13 | Qwen-Image-3.0-ProAlibaba | 1255±6 | 11,440 |
| 14 | MAI-Image-2.5Microsoft AI | 1254±4 | 61,265 |
| 15 | Gemini 3.1 Flash-Lite Image (nano-banana-2-lite)Google | 1250±6 | 17,804 |
| 16 | Gemini 3 Pro Image (nano-banana-pro, 2K)Google | 1248±3 | 175,734 |
| 17 | GPT-Image-1.5 (High Fidelity)OpenAI | 1237±3 | 169,927 |
| 18 | Gemini 3 Pro Image Preview (nano-banana-pro)Google | 1234±5 | 86,464 |
| 19 | Qwen-Image-2.1Alibaba | 1223±7prelim | 11,441 |
| 20 | Ideogram 4.0 (Quality)Ideogram | 1205±4 | 60,591 |
| 21 | Qwen-Image-2.0-Pro (2026-06-22)Alibaba | 1192±6 | 13,096 |
| 22 | UNI-1.1 MaxLuma AI | 1189±6 | 14,072 |
| 23 | UNI-1.1Luma AI | 1184±4 | 46,699 |
| 24 | MAI-Image-2Microsoft AI | 1184±5 | 51,475 |
| 25 | Grok Imagine ImageSpaceXAI | 1170±3 | 272,085 |
Arena Image Edit Leaderboard
arena.airanked by: Arena preference score (higher is better)Arena image-edit preference board: blind rankings for instruction fidelity and edit quality.
| # | Model | Arena score | Votes |
|---|---|---|---|
| 1 | GPT-Image-2.5 SunburstOpenAI | 1524±5prelim | 59,825 |
| 2 | GPT-Image-2.5 FlareOpenAI | 1481±5prelim | 57,408 |
| 3 | GPT-Image-2 (Medium)OpenAI | 1462±3 | 305,825 |
| 4 | Grok Imagine Image 2.0SpaceXAI | 1439±9prelim | 11,589 |
| 5 | MAI-Image-2.6Microsoft AI | 1428±5 | 51,384 |
| 6 | Gemini Nano Banana 2.1Google | 1428±6prelim | 12,985 |
| 7 | Grok Imagine Image 2.0 (20260801)SpaceXAI | 1425±5 | 50,427 |
| 8 | Muse ImageMeta | 1403±4 | 142,644 |
| 9 | MAI-Image-2.5Microsoft AI | 1401±4 | 190,081 |
| 10 | Seedream 5.0 ProBytedance | 1394±3 | 282,865 |
| 11 | Grok Imagine Image (Quality, 20260519)SpaceXAI | 1391±6 | 38,195 |
| 12 | Gemini 3 Pro Image (nano-banana-pro, 2K)Google | 1390±3 | 651,674 |
| 13 | ChatGPT Image Latest (High Fidelity, 20251216)OpenAI | 1389±3 | 629,464 |
| 14 | Gemini 3.1 Flash Image (nano-banana-2, Web Search)Google | 1387±3 | 229,782 |
| 15 | Gemini 3 Pro Image Preview (nano-banana-pro)Google | 1386±3 | 540,775 |
| 16 | Reve 2.1Reve | 1374±6 | 20,792 |
| 17 | GPT-Image-1.5 (High Fidelity)OpenAI | 1370±3 | 654,249 |
| 18 | Qwen-Image-2.1Alibaba | 1369±6prelim | 21,941 |
| 19 | Reve 2.0Reve | 1359±6 | 19,265 |
| 20 | Ideogram 4.5Ideogram | 1347±5prelim | 19,318 |
| 21 | UNI-1.1 MaxLuma AI | 1334±5 | 43,446 |
| 22 | Grok Imagine ImageSpaceXAI | 1329±2 | 756,681 |
| 23 | UNI-1.1Luma AI | 1315±3 | 188,834 |
| 24 | Gemini 3.1 Flash-Lite Image (nano-banana-2-lite)Google | 1314±5 | 65,669 |
| 25 | Qwen-Image-2.0-Pro (2026-06-22)Alibaba | 1303±5 | 56,723 |
Video Generation
2 boards · 96 entriesArena Text-to-Video Leaderboard
arena.airanked by: Arena preference score (higher is better)Arena text-to-video preference board: double-blind votes on motion quality, prompt adherence and aesthetics.
| # | Model | Arena score | Votes |
|---|---|---|---|
| 1 | Gemini Omni 1.1 FlashGoogle | 1516±15 | 1,784 |
| 2 | gemini-omni-flashGoogle | 1513±9 | 26,576 |
| 3 | FLUX 3 VideoBlack Forest Labs | 1493±17prelim | 1,302 |
| 4 | Grok Imagine Video 1.5SpaceXAI | 1492±18prelim | 1,218 |
| 5 | Dreamina Seedance 2.0 (720p)Bytedance | 1479±8 | 56,318 |
| 6 | Wan 3.0Alibaba | 1476±13 | 2,598 |
| 7 | Dreamina Seedance 2.5 (720p)Bytedance | 1474±9 | 8,001 |
| 8 | MiniMax H3MiniMax | 1460±9 | 11,417 |
| 9 | Muse VideoMeta | 1456±15 | 2,188 |
| 10 | HappyHorse 1.0Alibaba-ATH | 1427±13 | 22,264 |
| 11 | Sora 2 ProOpenAI | 1368±7 | 54,167 |
| 12 | Veo 3.1 (Audio)Google | 1364±14 | 13,741 |
| 13 | Veo 3.1 (Audio, 1080p)Google | 1362±10 | 25,076 |
| 14 | Veo 3.1 Fast (Audio)Google | 1362±10 | 39,484 |
| 15 | Veo 3.1 Fast (Audio, 1080p)Google | 1358±10 | 25,870 |
| 16 | Veo 3 Fast (Audio)Google | 1348±11 | 25,258 |
| 17 | Sora 2OpenAI | 1343±6 | 71,947 |
| 18 | Grok Imagine Video (720p)SpaceXAI | 1342±6 | 165,462 |
| 19 | Veo 3 (Audio)Google | 1340±13 | 19,002 |
| 20 | Wan 2.7Alibaba | 1337±7 | 27,626 |
| 21 | Wan 2.6Alibaba | 1327±7 | 54,050 |
| 22 | Seedance 1.5 ProBytedance | 1256±7 | 76,171 |
| 23 | Veo 3Google | 1254±11 | 15,005 |
| 24 | Veo 3 FastGoogle | 1248±12 | 15,283 |
| 25 | Wan 2.5 PreviewAlibaba | 1245±9 | 36,378 |
Arena Image-to-Video Leaderboard
arena.airanked by: Arena preference score (higher is better)Arena image-to-video preference board: double-blind votes on first-frame fidelity and motion plausibility.
| # | Model | Arena score | Votes |
|---|---|---|---|
| 1 | MiniMax H3MiniMax | 1495±5 | 57,112 |
| 2 | Gemini Omni 1.1 FlashGoogle | 1488±11 | 3,734 |
| 3 | Wan 3.0Alibaba | 1480±11 | 3,442 |
| 4 | Dreamina Seedance 2.5 (720p)Bytedance | 1477±7 | 15,729 |
| 5 | Dreamina Seedance 2.0 (720p)Bytedance | 1475±7 | 121,427 |
| 6 | gemini-omni-flashGoogle | 1465±6 | 87,155 |
| 7 | HiDream-O1-Video-1.0HiDream | 1456±8prelim | 6,488 |
| 8 | Grok Imagine Video 1.5 (720p)SpaceXAI | 1456±4 | 137,459 |
| 9 | FLUX 3 Video (20260811)Black Forest Labs | 1449±5 | 37,042 |
| 10 | HappyHorse 1.0Alibaba-ATH | 1442±10 | 70,640 |
| 11 | Wan 2.7Alibaba | 1428±5 | 85,521 |
| 12 | Grok Imagine Video (720p)SpaceXAI | 1415±4 | 554,050 |
| 13 | Veo 3.1 (Audio)Google | 1398±10 | 25,116 |
| 14 | Veo 3.1 (Audio, 1080p)Google | 1390±9 | 53,089 |
| 15 | Veo 3.1 Fast (Audio)Google | 1385±9 | 99,804 |
| 16 | Grok Imagine Video (480p)SpaceXAI | 1385±8 | 19,429 |
| 17 | Veo 3.1 Fast (Audio, 1080p)Google | 1372±9 | 54,380 |
| 18 | Vidu Q3 ProShengshu | 1363±9 | 36,679 |
| 19 | Kling 3.0 ProKlingAI | 1354±6 | 206,221 |
| 20 | Veo 3 (Audio)Google | 1331±12 | 32,367 |
| 21 | Veo 3 Fast (Audio)Google | 1326±10 | 41,194 |
| 22 | Wan 2.5 PreviewAlibaba | 1321±10 | 16,907 |
| 23 | Wan 2.6Alibaba | 1310±7 | 121,082 |
| 24 | Seedance 1.5 ProBytedance | 1307±7 | 245,206 |
| 25 | PixVerse V5.6 Proprietary | 1299±7 | 126,710 |
3D Generation
1 boards · 6 entriesT3 Bench 3D Generation Leaderboard
t3bench.comranked by: GPT-4V judged averageOfficial text-to-3D benchmark: GPT-4V-judged averages on single-object, single-with-surroundings and multi-object sets.
| # | Model | Average | Single Obj. | Single w/ Surr. | Multi Obj. |
|---|---|---|---|---|---|
| 1 | ProlificDreamer | 43.3 | 49.4 | 44.8 | 35.8 |
| 2 | Magic3D | 32.7 | 37 | 35.4 | 25.7 |
| 3 | LatentNeRF | 28.1 | 33.1 | 30.6 | 20.6 |
| 4 | Fantasia3D | 24 | 26.4 | 27 | 18.5 |
| 5 | DreamFusion | 21.7 | 24.4 | 24.6 | 16.1 |
| 6 | SJC | 18.7 | 24.7 | 19.8 | 11.7 |
As an Amazon Associate, we earn from qualifying purchases.