IT Home On October 19, the Arena (arena.ai) platform released the AI large model blind test rankings for the 42nd week of 2026 (2026-10-12 ~ 2026-10-18). This week, the top positions remained stable overall. Domestic models maintained mid-to-upper ranks on various sub-listings. Specifically, kimi-k3-max entered the top ten for the first time, and mimo-v2.6-pro made it into the top 20 for front-end development, showing quite impressive performance. Three new models were officially included in this list: gemini-3.5-flash-medium, mimo-v2.6-pro, and flux-2-flex.
IT Home Note: This ranking is based on anonymous blind voting on the Arena (arena.ai) platform, and the rankings are calculated using ELO (the agent ranking is a percentage signal). It reflects user subjective preferences rather than an absolute ability test. The different rankings are independent of each other, and comparisons across rankings should not be made. Any difference in scores within the error range is considered equivalent, and new models must accumulate a certain amount of votes before they can officially enter the list.
Comprehensive Rankings
The top position in the comprehensive ranking remains stable. Gemini-4-argon-high stays at number one with 1525 points, while Claude-opus-5.5-high is second with 1507 points. Claude-opus-4-6-high and Claude-Fable-5-high share third place with 1504 points, and the difference between them is within 30 points, so it is considered close competition within the error range. The scores of the top 10 models are all above 1494 points, indicating ongoing tight competition. The new model that entered the ranking this week is Gemini-3.5-flash-medium, which quickly reached the top 30, sitting at 30th place with an ELO score of 1476 points, showing excellent performance.
The domestic models are generally in a mid-to-upper tier, with a relatively stable hierarchy:
Moon's Dark Side kimi-k3-max has the highest ranking, at 16th place, with an ELO of 1488 points, and its ranking is stable.
Alibaba Qwen3.8-max is in 22nd place with ELO 1483 points, a levelly ranked position;
Xiaomi Mimo-V2.6-Pro is in 26th place with 1480 ELO points, maintaining the same ranking.
ZhiPu GLM-5.3-max is in 27th place with an ELO of 1478, maintaining the same ranking.
| Ranking | Compared to last week | Model | Manufacturer | Score (±CI) | Votes | Price ($/M) Input / Output | Context |
|---|---|---|---|---|---|---|---|
| 1 | - | gemini-4-argon-high | 1525 ±9 | 4892 | $2 / $10 | 1M | |
| 2 | - | claude-opus-5.5-high | Anthropic | 1507 ±8 | 6272 | $4 / $20 | 1M |
| 3 | - | claude-opus-4-6-high | Anthropic | 1504 ±3 | 79415 | $5 / $25 | 1M |
| 4 | - | claude-fable-5-high | Anthropic | 1504 ±4 | 40026 | $10 / $50 | 1M |
| 5 | - | claude-opus-4-7-high | Anthropic | 1501 ±4 | 65192 | $5 / $25 | 1M |
| 6 | - | claude-fable-5.1-max | Anthropic | 1501 ±6 | 13063 | $10 / $50 | 1M |
| 7 | - | claude-opus-4-6 | Anthropic | 1498 ±3 | 84095 | $5 / $25 | 1M |
| 8 | - | Gemini-3.8-flash-high | 1497 ±5 | 31437 | $0.75 / $3.75 | 1.05M | |
| 9 | - | muse-spark-1.3-max | Meta | 1494 ±6 | 14694 | $1.25 / $4.25 | 1M |
| 10 | - | claude-opus-4-7 | Anthropic | 1494 ±4 | 66315 | $5 / $25 | 1M |
| — The following are the Top 10 domestic models outside of Top. — | |||||||
| 16 | - | kimi-k3-max | Moonshot | 1488 ±5 | 30351 | N/A | N/A |
| 22 | - | qwen3.8-max | Alibaba | 1483 ±5 | 25378 | $2 / $6 | 1M |
| 26 | - | mimo-v2.6-pro | Xiaomi | 1480 ±9 | 4069 | $0.44 / $0.87 | 1.05M |
| 27 | - | glm-5.3-max | Z.ai | 1478 ±5 | 20049 | $1.4 / $4.4 | 1.05M |
Code List
The leading position in the code list remains stable. Gemini-4-argon-high continues to lead with 1562 points, while Claude-fable-5-high comes in second with 1551 points. Claude-opus-4-7-high, Claude-opus-4-6-high, and Claude-opus-5.5-high share third place with 1550 points each. Among the top three, all except Gemini-4-argon-high are Anthropic models, and the leading position is still held by foreign manufacturers. This week’s key highlight is that the domestic model kimi-k3-max has remained stable at tenth place, with an ELO of 1540 points, becoming the highest ranking for domestic models on the code list. Xiaomi mimo-v2.6-pro follows closely behind at eleventh place, with an ELO of 1539 points, showing impressive performance.
Several domestic models have made it onto the top 30 of the code list. The specific rankings are as follows:
Moon's Dark Side kimi-k3-max: Rank 10, ELO 1540 points, unchanged rank;
Xiaomi Mimo-V2.6-Pro is ranked 11th with 1539 ELO points, showing no change in rank.
Deep Seek deepseek-v4.1-flash-max, ranked 26th, with an ELO of 1528 points, no change in rank.
ZhiPu glm-5.3-flash is ranked 27th with 1525 ELO points, maintaining the same position.
Ali Qwen3.7-max-preview: 28th place, ELO 1524, no change in ranking;
Alibaba Qwen3.8-max: 29th place, ELO 1524, unchanged rank.
| Ranking | Compared to last week | Model | Manufacturer | Score (±CI) | Votes | Price ($/M) Input / Output | Context |
|---|---|---|---|---|---|---|---|
| 1 | - | gemini-4-argon-high | 1562 ±17 | 1233 | $2 / $10 | 1M | |
| 2 | - | claude-fable-5-high | Anthropic | 1551 ±7 | 10404 | $10 / $50 | 1M |
| 3 | - | claude-opus-4-7-high | Anthropic | 1550 ±6 | 18591 | $5 / $25 | 1M |
| 4 | - | claude-opus-4-6-high | Anthropic | 1550 ±6 | 20617 | $5 / $25 | 1M |
| 5 | - | claude-opus-5.5-high | Anthropic | 1550 ±16 | 1444 | $4 / $20 | 1M |
| 6 | - | claude-opus-4-6 | Anthropic | 1548 ±5 | 23351 | $5 / $25 | 1M |
| 7 | - | claude-opus-4-7 | Anthropic | 1546 ±6 | 18816 | $5 / $25 | 1M |
| 8 | - | gpt-6.1-sol-max | OpenAI | 1545 ±20 | 911 | $2 / $10 | 1.05M |
| 9 | - | gpt-6-astra-max | OpenAI | 1542 ±12 | 2424 | N/A | N/A |
| 10 | - | kimi-k3-max | Moonshot | 1540 ±7 | 7775 | N/A | N/A |
| — The following are the Top 10 domestic models outside of Top. — | |||||||
| 11 | - | mimo-v2.6-pro | Xiaomi | 1539 ±18 | 1107 | $0.44 / $0.87 | 1.05M |
| 26 | - | deepseek-v4.1-flash-max | DeepSeek | 1528 ±11 | 3026 | $0.3 / $1.2 | 1M |
| 27 | - | glm-5.3-flash | Z.ai | 1525 ±8 | 7267 | $0.06 / $0.2 | 1.05M |
| 28 | - | qwen3.7-max-preview | Alibaba | 1524 ±18 | 1165 | $1.48 / $4.43 | 1M |
| 29 | - | qwen3.8-max | Alibaba | 1524 ±8 | 7077 | $2 / $6 | 1M |
Frontend Development Rankings
The front-end development leaderboard has a stable top position. Claude-opus-5.5-max stands at the top with 1813 points, GPT-6-astra-max is second with 1786 points, and Claude-sonnet-5.5-xhigh is third with 1774 points. New models that made it onto the list this week include mimo-v2.6-pro and Claude-haiku-5.5-high. Xiaomi’s mimo-v2.6-pro entered the list as number 19 with ELO 1629 points, successfully entering the top 20 and continuing its good performance in the code domain.
Domestic models occupy several mid-to-upper positions on the frontend development list, specifically as follows:
Ali Qwen3.8-max-0902 is in 10th place, with an ELO of 1674 points, a flat ranking.
Alibaba Qwen3.8-max is in 11th place with 1672 ELO points, maintaining the same ranking.
Moon's Dark Side kimi-k3-max is in 14th place, with an ELO of 1654 points, and the ranking remains unchanged;
Xiaomi Mimo-V2.6-Flash is in 16th place, with an ELO of 1637 points, and the ranking remains unchanged.
Ali Qwen3.8-flash-next is in 17th place with 1633 ELO points, maintaining the same rank;
Tencent hy4-preview is in 18th place with 1632 ELO points, maintaining the same ranking;
Xiaomi Mimo-V2.6-Pro ranked 19th on the new list, with an ELO score of 1629.
ZhiPu GLM-5.3-max is in 22nd place with 1622 ELO points, maintaining the same ranking.
| Ranking | Compared to last week | Model | Manufacturer | Score (±CI) | Votes | Price ($/M) Input / Output | Context |
|---|---|---|---|---|---|---|---|
| 1 | - | claude-opus-5.5-max | Anthropic | 1813 ±15 | 2294 | $4 / $20 | 1M |
| 2 | - | gpt-6-astra-max | OpenAI | 1786 ±11 | 5189 | $10 / $50 | 1.05M |
| 3 | - | claude-sonnet-5.5-xhigh | Anthropic | 1774 ±15 | 2323 | $2 / $10 | 1M |
| 4 | - | gpt-6.1-sol-max | OpenAI | 1755 ±15 | 2102 | $2 / $10 | 1.05M |
| 5 | - | claude-fable-5.1-max | Anthropic | 1744 ±9 | 6663 | $10 / $50 | 1M |
| 6 | - | claude-sonnet-5.5-high | Anthropic | 1715 ±11 | 3984 | $2 / $10 | 1M |
| 7 | - | claude-opus-5-max | Anthropic | 1691 ±6 | 17320 | $5 / $25 | 1M |
| 8 | - | gpt-6-sol-max | OpenAI | 1688 ±12 | 3407 | $2 / $10 | 1.05M |
| 9 | - | gemini-4-argon-high | 1678 ±15 | 1771 | $2 / $10 | 1M | |
| 10 | - | qwen3.8-max-0902 | Alibaba | 1674 ±8 | 11182 | $2 / $6 | N/A |
| — The following are the Top 10 domestic models outside of Top. — | |||||||
| 11 | - | qwen3.8-max | Alibaba | 1672 ±12 | 3446 | $2 / $6 | 1M |
| 14 | - | kimi-k3-max | Moonshot | 1654 ±6 | 17412 | $3 / $15 | 1.05M |
| 16 | - | mimo-v2.6-flash | Xiaomi | 1637 ±10 | 4058 | $0.14 / $0.28 | 1.05M |
| 17 | - | qwen3.8-flash-next | Alibaba | 1633 ±8 | 6932 | $0.16 / $0.47 | 1M |
| 18 | - | hy4-preview | Tencent | 1632 ±10 | 4792 | $0.75 / $2.25 | 1.05M |
| 19 | New release | mimo-v2.6-pro | Xiaomi | 1629 ±11 | 3649 | $0.44 / $0.87 | 1.05M |
| 22 | - | glm-5.3-max | Z.ai | 1622 ±8 | 8382 | $1.4 / $4.4 | 1.05M |
| 23 | - | deepseek-v4.1-flash-max | DeepSeek | 1619 ±11 | 3542 | $0.3 / $1.2 | 1M |
| 26 | - | glm-5.3-flash | Z.ai | 1609 ±7 | 13697 | $0.06 / $0.2 | 1.05M |
| 27 | - | glm-5.2-max | Z.ai | 1603 ±6 | 15351 | $1.4 / $4.4 | 1M |
AI Ranking
The AI leaderboard uses a percentage signal scoring system. This week, Claude Opus 5.5 (Max) remains at the top with a net improvement of 15.53%, GPT 6 Astra (Max) rose one place to second with a net improvement of 13.09%, and Claude Fable 5.1 (Max) ranks third with a net improvement of 12.66%. The top positions are still occupied by overseas models. In terms of metrics, the tool hallucination rate of Claude Opus 5.5 (Max) is only 0.37%, the lowest among the leaders, indicating excellent performance. Domestic models are generally in the mid-to-upper tier, with several of them entering the top 30.
The specific performance of domestic models on the agent rankings is as follows:
Deepseek V4.1 Flash (Max) ranked 15th, with a net improvement of 3.80%, and a task confirmation success rate of 7.44%. It rose 2 positions compared to last week;
Moon's Dark Side Kimi K3 (Max) ranked 16th, with a net improvement of 3.78%, and a task confirmation success rate of 6.46%, rising 2 places compared to last week;
Tencent Hy4 preview: Ranked 17, with a net improvement of 3.61%, and a task confirmation success rate of 5.96%. It rose 2 positions compared to last week.
Xiaomi MiMo V2.6 Pro ranked 18th, with a net improvement of 3.52%, and a task confirmation success rate of 8.03%. It rose 2 places compared to last week.
ZhiPu GLM 5.2 (Max) ranked 19th, with a net improvement of 3.19%, and a task confirmation success rate of 4.11%. It rose 2 places compared to last week;
Alibaba Qwen3.8 Max: Ranked 22nd, with a net improvement of 2.35%, and a task confirmation success rate of 5.09%. It rose 2 positions compared to last week.
ZhiPu GLM 5.3 (Max) ranked 23rd, with a net improvement of 2.15%, and a task confirmation success rate of 4.78%. It rose 2 positions compared to last week.
| Ranking | Compared to last week | Model | Manufacturer | Net Improvement (±CI) | Task Confirmation Success Rate | Positive Reviews / Negative Ratings | Controllability |
|---|---|---|---|---|---|---|---|
| 1 | - | Claude Opus 5.5 (Max) | Anthropic | 15.53% ±4.63% | 17.29% ±6.02% | 36.78% ±20.55% | 8.2% ±4.06% |
| 2 | ↑ 1 | GPT 6 Astra (Max) | OpenAI | 13.09% ±2.37% | 12.13% ±3.88% | 38.54% ±9.96% | 8.85% ±2.5% |
| 3 | ↑ 1 | Claude Fable 5.1 (Max) | Anthropic | 12.66% ±2.05% | 16.19% ±2.96% | 26.22% ±7.98% | 8.84% ±3.12% |
| 4 | ↑ 1 | Claude Sonnet 5.5 (Max) | Anthropic | 11.95% ±3.31% | 15.83% ±5.06% | 23.37% ±14.09% | 5.1% ±3.33% |
| 5 | ↑ 1 | GPT 6.1 Sol (Max) | OpenAI | 11.72% ±3.05% | 14.74% ±4.18% | 30.32% ±12.99% | 8.52% ±3.07% |
| 6 | ↑ 1 | GPT 6 Sol (Max) | OpenAI | 9.92% ±2.38% | 6.97% ±4.34% | 23.55% ±9.64% | 11.92% ±2.02% |
| 7 | ↑ 1 | Gemini 4 Argon (High) | 9.26% ±2.36% | 15.64% ±3.26% | 40.6% ±9.56% | 11.64% ±2.1% | |
| 8 | ↑ 1 | Claude Fable 5 (High) | Anthropic | 8.94% ±1.27% | 5.79% ±2.6% | 19.34% ±4.8% | 9.49% ±1.39% |
| 9 | ↑ 1 | Claude Opus 5 (Max) | Anthropic | 8.12% ±1.47% | 10.42% ±3.1% | 11.86% ±5.46% | 4.22% ±2.01% |
| 10 | ↑ 2 | Claude Opus 4.8 (High) | Anthropic | 7.13% ±1.37% | 4.68% ±2.75% | 15.14% ±5.03% | 8.41% ±1.6% |
| — The following are the Top 10 domestic models outside of Top. — | |||||||
| 15 | ↑ 2 | Deepseek V4.1 Flash (Max) | DeepSeek | 3.8% ±0.39% | 7.44% ±0.86% | 2.44% ±1.45% | 0.87% ±0.54% |
| 16 | ↑ 2 | Kimi K3 (Max) | Moonshot | 3.78% ±0.59% | 6.46% ±1.32% | 6.44% ±2.05% | 1.14% ±0.86% |
| 17 | ↑ 2 | Hy4 preview | Tencent | 3.61% ±0.7% | 5.96% ±1.48% | 5.18% ±2.59% | 0.32% ±0.92% |
| 18 | ↑ 2 | MiMo V2.6 Pro | Xiaomi | 3.52% ±1.92% | 8.03% ±3.88% | 8.16% ±7.31% | 0.56% ±2.45% |
| 19 | ↑ 2 | GLM 5.2 (Max) | Z.ai | 3.19% ±0.73% | 4.11% ±1.58% | 8.94% ±2.61% | 1.72% ±0.96% |
| 22 | ↑ 2 | Qwen3.8 Max | Alibaba | 2.35% ±0.59% | 5.09% ±1.32% | 2.95% ±2.13% | 1.81% ±0.82% |
| 23 | ↑ 2 | GLM 5.3 (Max) | Z.ai | 2.15% ±0.72% | 4.78% ±1.62% | 5.12% ±2.48% | 0.44% ±1.08% |
| 25 | ↑ 2 | DeepSeek V4 Pro (High) (0813) | DeepSeek | 1.34% ±1.66% | 2% ±4.01% | 1.86% ±5.99% | 2.12% ±2.2% |
AI Image Generation Rankings
The top position in the AI image generation rankings is stable. gpt-image-2.5-sunburst remains at the top with 1425 points, gpt-image-2.5-flare is second with 1398 points, and gpt-image-2 (medium) is third with 1383 points. All three top positions are occupied by OpenAI models. The new model that entered the rankings this week is flux-2-flex, which ranked 30th upon its first appearance in the rankings, with an ELO score of 1157 points. Domestic models perform steadily in this ranking; ByteDance’s seedream-5.0-pro and Alibaba’s qwen-image-3.0-pro both rank 12th and 13th with 1255 points respectively, both entering the top 15 and positioned in the mid-to-upper range.
| Ranking | Compared to last week | Model | Manufacturer | Score (±CI) | Votes | Price ($/M) Input / Output | Context |
|---|---|---|---|---|---|---|---|
| 1 | - | gpt-image-2.5-sunburst | OpenAI | 1425 ±7 | 17752 | N/A | N/A |
| 2 | - | gpt-image-2.5-flare | OpenAI | 1398 ±7 | 16889 | N/A | N/A |
| 3 | - | gpt-image-2 (medium) | OpenAI | 1383 ±4 | 93334 | $8 / $30 | N/A |
| 4 | - | grok-imagine-image-2.0 (canvas) | SpaceXAI | 1334 ±12 | 3113 | N/A | N/A |
| 5 | - | mai-image-2.6 | Microsoft AI | 1332 ±5 | 25091 | N/A | N/A |
| 6 | - | gemini-nano-banana-2.1 | 1328 ±9 | 5310 | $1.5 / $7.5 | 65.5K | |
| 7 | - | reve-2.1 | Reve | 1302 ±8 | 8249 | N/A | N/A |
| 8 | - | grok-imagine-image-2.0 (20260801) | SpaceXAI | 1294 ±6 | 14483 | N/A | N/A |
| 9 | - | muse-image | Meta | 1274 ±5 | 42262 | N/A | N/A |
| 10 | - | reve-2.0 | Reve | 1269 ±6 | 15773 | N/A | N/A |
| — The following are the Top 10 domestic models outside of Top. — | |||||||
| 12 | - | seedream-5.0-pro | Bytedance | 1255 ±4 | 94181 | N/A | N/A |
| 13 | - | qwen-image-3.0-pro | Alibaba | 1255 ±6 | 11440 | N/A | N/A |
| 19 | - | qwen-image-2.1 | Alibaba | 1223 ±7 | 11441 | N/A | N/A |
| 21 | - | qwen-image-2.0-pro-2026-06-22 | Alibaba | 1192 ±6 | 13096 | N/A | N/A |
AI Video Rankings
The top spot on the AI video rankings is still held by the Google model. Gemini-OMNI-1.1-Flash ranks first with 1516 points, Gemini-OMNI-Flash comes in second with 1513 points, and Flux-3-Video is third with 1493 points. Domestic models perform exceptionally well, taking two of the top five places. ByteDance’s Dreamina-Seedance-2.0-720p ranks fifth with ELO 1479 points, followed by Alibaba’s Wan3.0 in sixth place with ELO 1476 points. Four domestic models make up the top 10, and their overall strength is significant.
| Ranking | Compared to last week | Model | Manufacturer | Score (±CI) | Votes | Price ($/M) Input / Output | Context |
|---|---|---|---|---|---|---|---|
| 1 | - | gemini-omni-1.1-flash | 1516 ±15 | 1784 | $1.5 / $9 | N/A | |
| 2 | - | gemini-omni-flash | 1513 ±9 | 26576 | N/A | N/A | |
| 3 | - | flux-3-video | Black Forest Labs | 1493 ±17 | 1302 | N/A | N/A |
| 4 | - | grok-imagine-video-1.5-agent | SpaceXAI | 1492 ±18 | 1218 | N/A | N/A |
| 5 | - | dreamina-seedance-2.0-720p | Bytedance | 1479 ±8 | 56318 | N/A | N/A |
| 6 | - | wan3.0 | Alibaba | 1476 ±13 | 2598 | N/A | N/A |
| 7 | - | dreamina-seedance-2.5-720p | Bytedance | 1474 ±9 | 8001 | N/A | N/A |
| 8 | - | minimax-h3 | MiniMax | 1460 ±9 | 11417 | N/A | N/A |
| 9 | - | muse-video | Meta | 1456 ±15 | 2188 | N/A | N/A |
| 10 | - | happyhorse-1.0 | Alibaba-ATH | 1427 ±13 | 22264 | N/A | N/A |
| — The following are the Top 10 domestic models outside of Top. — | |||||||
| 20 | - | wan2.7-t2v | Alibaba | 1337 ±7 | 27626 | N/A | N/A |
| 21 | - | wan2.6-t2v | Alibaba | 1327 ±7 | 54050 | N/A | N/A |
| 22 | - | seedance-v1.5-pro | Bytedance | 1256 ±7 | 76171 | N/A | N/A |
| 25 | - | wan2.5-t2v-preview | Alibaba | 1245 ±9 | 36378 | N/A | N/A |
This week, there were little changes in the overall top positions on the Arena AI large model rankings. Overseas models still occupy the top spot, while domestic models have firmly established themselves in the mid-to-upper tier on multiple sub-rankings. kimi-k3-max made it into the top ten on the code ranking, and mimo-v2.6-pro performed exceptionally well in both frontend development and AI agent rankings. ByteDance and Alibaba’s domestic models also maintained top-five and top-ten positions in the fields of AI image generation and AI video. We will continue to monitor the progress of domestic large models and bring you the latest ranking updates.