Kategoria ya AI BENCHY
Orodha ya Mahususi kwa domeni
Ona ni modeli gani za AI zinafanya vizuri zaidi katika Mahususi kwa domeni, zipi zinabaki thabiti, na pengo kubwa liko wapi. Panga kwa: Muda wa majibu (wastani) ↓.
Sababu zinazohusiana za kushindwa
| Nafasi | Modeli | Kampuni | Alama ya Mahususi kwa domeni | Wastani wa alama | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|
| #43 | MiniMax M2.5 medium | Minimax | 10.0 | 4.7 | 0/3 | 237.3s |
| #34 | GPT-5 Nano medium | OpenAI | 4.0 | 5.5 | 1/3 | 204.0s |
| #52 | GLM 4.7 Flash medium | Z.ai | 10.0 | 3.1 | 0/3 | 174.6s |
| #13 | Step 3.5 Flash medium | Stepfun | 4.0 | 7.4 | 1/3 | 170.5s |
| #24 | Qwen3.5-Flash medium | Qwen | 4.0 | 6.9 | 1/3 | 146.5s |
| #28 | Kimi K2.5 medium | Moonshot AI | 10.0 | 6.4 | 0/3 | 137.3s |
| #8 | Gemini 3.1 Flash Lite Preview high | 4.0 | 8.2 | 1/3 | 127.6s | |
| #30 | Grok 4.1 Fast medium | X AI | 4.0 | 6.2 | 1/3 | 121.8s |
| #21 | MiMo-V2-Flash medium | Xiaomi | 4.0 | 7.2 | 1/3 | 96.0s |
| #35 | Qwen3.5-35B-A3B medium | Qwen | 10.0 | 5.5 | 0/3 | 88.3s |
| #26 | Claude Opus 4.6 medium | Anthropic | 10.0 | 6.6 | 0/3 | 83.4s |
| #7 | Qwen3.5-27B medium | Qwen | 4.0 | 8.2 | 1/3 | 79.5s |
| #27 | GPT-5.2 medium | OpenAI | 4.0 | 6.5 | 1/3 | 77.8s |
| #9 | GPT-5.4 medium | OpenAI | 4.0 | 8.0 | 1/3 | 74.3s |
| #3 | GPT-5.3-Codex medium | OpenAI | 4.0 | 8.4 | 1/3 | 64.3s |
| #10 | Qwen3.5-122B-A10B medium | Qwen | 10.0 | 7.7 | 0/3 | 63.4s |
| #39 | gpt-oss-120b medium | OpenAI | 10.0 | 5.1 | 0/3 | 50.9s |
| #32 | GPT-5 Mini medium | OpenAI | 10.0 | 6.0 | 0/3 | 44.6s |
| #18 | DeepSeek V3.2 medium | DeepSeek | 4.0 | 7.3 | 1/3 | 39.3s |
| #16 | Gemini 2.5 Flash medium | 4.0 | 7.4 | 1/3 | 37.3s | |
| #2 | Gemini 3.1 Pro Preview medium | 7.0 | 9.4 | 2/3 | 32.7s | |
| #1 | Gemini 3 Flash Preview medium | 10.0 | 10.0 | 3/3 | 21.1s | |
| #15 | GPT-5.2 Chat none | OpenAI | 4.0 | 7.4 | 1/3 | 17.8s |
| #4 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 4.0 | 8.3 | 1/3 | 17.5s |
| #19 | GPT-5.3 Chat none | OpenAI | 10.0 | 7.3 | 0/3 | 13.0s |
| #5 | Gemini 3 Flash Preview low | 4.0 | 8.2 | 1/3 | 8.05s | |
| #6 | Gemini 3 Pro Preview medium | 4.0 | 8.2 | 1/3 | 7.01s | |
| #36 | Mercury 2 medium | Inception | 10.0 | 5.3 | 0/3 | 6.48s |
| #46 | Kimi K2.5 none | Moonshot AI | 4.0 | 4.1 | 1/3 | 4.38s |
| #12 | Gemini 3.1 Flash Lite Preview medium | 10.0 | 7.5 | 0/3 | 4.21s | |
| #25 | Claude Sonnet 4.6 none | Anthropic | 7.0 | 6.8 | 2/3 | 3.54s |
| #17 | Gemini 3.1 Flash Lite Preview low | 4.0 | 7.3 | 1/3 | 2.36s | |
| #31 | GLM 5 none | Z.ai | 10.0 | 6.0 | 0/3 | 2.24s |
| #33 | DeepSeek V3.2 none | DeepSeek | 10.0 | 5.5 | 0/3 | 1.61s |
| #29 | Qwen3.5 Plus 2026-02-15 none | Qwen | 4.0 | 6.2 | 1/3 | 1.17s |
| #44 | GPT-5.4 none | OpenAI | 4.0 | 4.5 | 1/3 | 1.07s |
| #53 | Grok 4.1 Fast none | X AI | 4.0 | 2.9 | 1/3 | 1.06s |
| #20 | Gemini 3 Flash Preview none | 7.0 | 7.2 | 2/3 | 963ms | |
| #48 | Qwen3 Coder Next none | Qwen | 4.0 | 4.0 | 1/3 | 962ms |
| #22 | Gemini 3.1 Flash Lite Preview none | 4.0 | 7.1 | 1/3 | 942ms | |
| #37 | Qwen3.5-Flash none | Qwen | 7.0 | 5.2 | 2/3 | 905ms |
| #45 | Trinity Large Preview none | Arcee AI | 4.0 | 4.2 | 1/3 | 877ms |
| #49 | GLM 4.7 Flash none | Z.ai | 7.0 | 3.9 | 2/3 | 744ms |
| #50 | Qwen3 Coder Next medium | Qwen | 4.0 | 3.5 | 1/3 | 638ms |
| #47 | GPT-4o-mini none | OpenAI | 10.0 | 4.0 | 0/3 | 637ms |
| #54 | MiMo-V2-Flash none | Xiaomi | 4.0 | 2.9 | 1/3 | 564ms |
| #41 | Qwen3.5-27B none | Qwen | 10.0 | 4.9 | 0/3 | 540ms |
| #51 | Mercury 2 none | Inception | 4.0 | 3.4 | 1/3 | 534ms |
| #38 | Gemini 2.5 Flash none | 4.0 | 5.2 | 1/3 | 495ms | |
| #42 | Qwen3.5-35B-A3B none | Qwen | 7.0 | 4.7 | 2/3 | 485ms |
| #40 | Qwen3.5-122B-A10B none | Qwen | 4.0 | 5.0 | 1/3 | 465ms |
| #55 | LFM2-24B-A2B none | Liquid | 4.0 | 2.6 | 1/3 | 287ms |
| #11 | Claude Sonnet 4.6 medium | Anthropic | 10.0 | 7.7 | 0/3 | 0ms |
| #14 | GLM 5 medium | Z.ai | 10.0 | 7.4 | 0/3 | 0ms |
| #23 | Seed-2.0-Mini medium | Bytedance Seed | 10.0 | 6.9 | 0/3 | 0ms |