claude-opus-4-7
83.5%±1.7%
81.8%CI85.2%
aiqbench · Benchmark-uri LLM
Benchmark-uri
- Surse
- 8
- Intrări urmărite
- 22.318
- Ultima sincronizare
- 30 minacum 30 de minute
Toate sursele se sincronizează normal
- Arena · Text· acum 7 ore
- Arena · WebDev· acum 7 ore
- Arena · Vision· acum 7 ore
- Arena · Agent· acum 7 ore
- GPQA Diamond· acum 30 de minute
- SWE-bench· acum 30 de minute
- Terminal-Bench· acum 30 de minute
- ARC-AGI-2· acum 30 de minute
Filtrează după organizație:
Lansat:
gpt-5.5-pre-release
80.6%±1.8%
78.8%CI82.4%
gemini-3.5-flash
79.3%±1.8%
77.5%CI81.2%
O singură grilă, toate coloanele. Alege axe din panoul Axe — o axă clasifică precum un singur clasament, mai multe se combină într-un scor compus ponderat, toate la un loc se citesc ca indexul. Locul este atribuit înaintea oricărui filtru și nu se renumerotează niciodată.
| Model | Organizație | ± CI | Oscilație | Adaugă la comparație | |||||
|---|---|---|---|---|---|---|---|---|---|
| 1 | claude-opus-4-7 | Anthropic | sept. 2026 | $5 / $25 | 83.5% | 81.8%–85.2% | #1–18 | ||
| 2 | gpt-5.5-pre-release | OpenAI | — | — | 80.6% | 78.8%–82.4% | #22–36 | ||
| 3 | gemini-3.5-flash | Google DeepMind | sept. 2026 | $1.50 / $9 | 79.3% | 77.5%–81.2% | #10–26 | ||
| 4 | claude-opus-4-6 | Anthropic | sept. 2026 | $5 / $25 | 78.7% | 76.9%–80.6% | #2–25 | ||
| 5 | glm-5.2 | Z.ai (Zhipu AI) | iun. 2026 | $0.62 / $2.42 | 78.7% | 76.8%–80.6% | #9–49 | ||
| 6 | deepseek-v4-pro | DeepSeek | aug. 2026 | $0.66 / $1.98 | 77.6% | 75.7%–79.5% | #17–55 | ||
| 7 | qwen3.7-max | Alibaba | mai 2026 | $1.48 / $4.42 | 77.3% | 75.4%–79.2% | #41–128 | ||
| 8 | gpt-5.4-2026-03-05 | OpenAI | sept. 2026 | $2.50 / $15 | 76.9% | 74.9%–78.8% | #12–27 | ||
| 9 | claude-opus-4-5-20251101 | Anthropic | nov. 2025 | $5 / $25 | 76.7% | 74.7%–78.6% | #19–62 | ||
| 10 | kimi-k2.6 | Moonshot | apr. 2026 | $0.65 / $3.41 | 76.7% | 74.7%–78.6% | #30–77 | ||
| 11 | qwen3.6-max-preview | Alibaba | oct. 2026 | — | 76.7% | 74.7%–78.6% | #33–53 | ||
| 12 | gemini-3.1-pro-preview-customtools | Google DeepMind | — | $2 / $12 | 75.6% | 73.7%–77.6% | #52–154 | ||
| 13 | gemini-3-flash-preview | Google DeepMind | — | $0.50 / $3 | 75.4% | 73.5%–77.4% | #27–99 | ||
| 14 | claude-sonnet-4-6 | Anthropic | sept. 2026 | $3 / $15 | 75.2% | 73.2%–77.2% | #39–78 | ||
| 15 | gpt-5.3-codex | OpenAI | oct. 2026 | $1.75 / $14 | 74.8% | 72.8%–76.8% | #29–236 | ||
| 16 | glm-5.1 | Z.ai (Zhipu AI) | apr. 2026 | $0.97 / $3.04 | 74.2% | 72.2%–76.2% | #44–75 | ||
| 17 | gpt-5.2-2025-12-11 | OpenAI | dec. 2025 | $1.75 / $14 | 73.8% | 71.8%–75.8% | #34–93 | ||
| 18 | kimi-k2.5 | Moonshot | ian. 2026 | $0.50 / $2.50 | 73.8% | 71.8%–75.8% | #70–446 | ||
| 19 | gpt-5-2025-08-07 | OpenAI | aug. 2025 | $1.25 / $10 | 73.6% | 71.5%–75.6% | #64–149 | ||
| 20 | claude-opus-4-1-20250805 | Anthropic | aug. 2025 | $15 / $75 | 73.3% | 71.3%–75.4% | #73–404 | ||
| 21 | gemini-3-pro-preview | Google DeepMind | — | — | 72.9% | 70.9%–75.0% | #19–120 | ||
| 22 | glm-5 | Z.ai (Zhipu AI) | feb. 2026 | $1 / $3.20 | 72.1% | 70.0%–74.2% | #57–153 | ||
| 23 | claude-sonnet-4-5-20250929 | Anthropic | sept. 2025 | $3 / $15 | 71.3% | 69.2%–73.3% | #66–232 | ||
| 24 | claude-opus-4-20250514 | Anthropic | mai 2025 | — | 70.7% | 68.6%–72.7% | #84–469 | ||
| 25 | gpt-5.1-2025-11-13 | OpenAI | nov. 2025 | $1.25 / $10 | 68.0% | 65.9%–70.1% | #45–242 | ||
| 26 | gpt-5-mini-2025-08-07 | OpenAI | aug. 2025 | $0.25 / $2 | 64.7% | 62.5%–66.8% | #126–343 | ||
| 27 | o3-2025-04-16 | OpenAI | apr. 2025 | $2 / $8 | 62.3% | 60.1%–64.5% | #79–318 | ||
| 28 | claude-3-7-sonnet-20250219 | Anthropic | feb. 2025 | — | 61.0% | 58.7%–63.2% | #128–358 | ||
| 29 | qwen3.6-plus | Alibaba | oct. 2026 | $0.33 / $1.95 | 57.9% | 55.6%–60.1% | #47–265 | ||
| 30 | gemini-2.5-pro | Google DeepMind | iun. 2025 | $1.25 / $10 | 57.6% | 55.3%–59.8% | #60–432 | ||
| 31 | gpt-4.1-2025-04-14 | OpenAI | apr. 2025 | $2 / $8 | 48.5% | 46.3%–50.8% | #148–545 | ||
| 32 | gpt-4o-2024-11-20 | OpenAI | mai 2024 | $2.50 / $10 | 31.0% | 28.9%–33.1% | #154–955 |
Se afișează SWE-bench Verified exact așa cum a publicat-o sursa — propriul scor și interval de încredere, fără mix. Selectează o a doua axă ca să construiești un scor compus ponderat.