gemini-4-argon
76.0%±1.4%
74.6%CI77.4%
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 33 min33 minutes ago
All sources syncing normally
- Arena · Text· 1 hour ago
- Arena · WebDev· 1 hour ago
- Arena · Vision· 1 hour ago
- Arena · Agent· 1 hour ago
- GPQA Diamond· 33 minutes ago
- SWE-bench· 33 minutes ago
- Terminal-Bench· 33 minutes ago
- ARC-AGI-2· 33 minutes ago
Filter by org:
Released:
gpt-6-astra
75.6%±1.4%
74.2%CI77.0%
gpt-6.1-sol
73.9%±1.4%
72.5%CI75.3%
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | ± CI | Swing | Add to compare | |||||
|---|---|---|---|---|---|---|---|---|---|
| 1 | gemini-4-argon | Google DeepMind | Oct 2026 | $2 / $10 | 76.0% | 74.6%–77.4% | #1–10 | ||
| 2 | gpt-6-astra | OpenAI | Sep 2026 | $10 / $50 | 75.6% | 74.2%–77.0% | #1–18 | ||
| 3 | gpt-6.1-sol | OpenAI | Oct 2026 | $2 / $10 | 73.9% | 72.5%–75.3% | #1–15 | ||
| 4 | gemini-3.1-pro-preview | Google DeepMind | Sep 2026 | $2 / $12 | 73.5% | 72.1%–74.9% | #9–36 | ||
| 5 | claude-opus-5-5 | Anthropic | Oct 2026 | $4 / $20 | 72.2% | 70.8%–73.6% | #2–11 | ||
| 6 | claude-fable-5-1 | Anthropic | Sep 2026 | $10 / $50 | 70.8% | 69.4%–72.2% | #2–21 | ||
| 7 | claude-fable-5 | Anthropic | Sep 2026 | $10 / $50 | 70.7% | 69.3%–72.1% | #4–20 | ||
| 8 | gemini-3.8-flash | Google DeepMind | Oct 2026 | $0.83 / $4.13 | 69.7% | 68.2%–71.2% | #2–29 | ||
| 9 | gpt-5.6-sol | OpenAI | Sep 2026 | $4 / $20 | 69.7% | 68.2%–71.2% | #6–25 | ||
| 10 | gemini-3.7-flash | Google DeepMind | Oct 2026 | $0.75 / $3.75 | 69.2% | 67.7%–70.7% | #9–57 | ||
| 11 | gemini-3-flash-preview | Google DeepMind | — | $0.50 / $3 | 66.8% | 65.3%–68.3% | #27–99 | ||
| 12 | gemini-3.5-flash | Google DeepMind | Sep 2026 | $1.50 / $9 | 66.2% | 64.7%–67.7% | #10–26 | ||
| 13 | gemini-3.6-flash | Google DeepMind | Sep 2026 | $0.75 / $3.75 | 66.2% | 64.7%–67.7% | #16–95 | ||
| 14 | gpt-5.5 | OpenAI | Sep 2026 | $5 / $30 | 63.0% | 61.5%–64.5% | #9–34 | ||
| 15 | gpt-6-sol | OpenAI | Oct 2026 | $2 / $10 | 60.7% | 59.2%–62.2% | #7–53 | ||
| 16 | muse-spark-1.2 | Meta AI | Oct 2026 | $1.25 / $4.25 | 60.3% | 58.7%–61.9% | #13–112 | ||
| 17 | claude-opus-5 | Anthropic | Sep 2026 | $5 / $25 | 59.9% | 58.3%–61.5% | #5–11 | ||
| 18 | muse-spark-1.1 | Meta AI | Sep 2026 | $1.25 / $4.25 | 57.8% | 56.2%–59.4% | #21–115 | ||
| 19 | Muse-Spark-Open-816B-A42B | Meta AI | — | — | 56.6% | 55.0%–58.2% | #54–119 | ||
| 20 | grok-4.7 | xAI | Oct 2026 | $2 / $6 | 56.0% | 54.4%–57.6% | #21–72 | ||
| 21 | qwen3.7-max | Alibaba | May 2026 | $1.48 / $4.42 | 55.8% | 54.2%–57.3% | #41–128 | ||
| 22 | claude-opus-4-8 | Anthropic | Sep 2026 | $5 / $25 | 53.0% | 51.4%–54.6% | #15–33 | ||
| 23 | deepseek-v4-pro-0813 | DeepSeek | Aug 2026 | $0.66 / $1.98 | 52.9% | 51.3%–54.5% | #40–130 | ||
| 24 | qwen3.6-max-preview | Alibaba | Oct 2026 | — | 52.0% | 50.4%–53.6% | #34–53 | ||
| 25 | claude-opus-4-7 | Anthropic | Sep 2026 | $5 / $25 | 51.7% | 50.1%–53.3% | #1–18 | ||
| 26 | kimi-k3 | Moonshot | Jun 2026 | $0.25 / $11.94 | 50.6% | 49.0%–52.2% | #10–39 | ||
| 27 | gpt-5-2025-08-07 | OpenAI | Aug 2025 | $1.25 / $10 | 50.1% | 48.5%–51.7% | #64–149 | ||
| 28 | o3-2025-04-16 | OpenAI | Apr 2025 | $2 / $8 | 49.4% | 47.8%–51.0% | #79–318 | ||
| 29 | grok-4.6 | xAI | Sep 2026 | $2 / $6 | 49.3% | 47.7%–50.9% | #15–52 | ||
| 30 | qwen3-max-2025-09-23 | Alibaba | Sep 2025 | — | 48.7% | 47.2%–50.3% | #81–167 | ||
| 31 | grok-4.5 | xAI | Sep 2026 | $2 / $6 | 48.3% | 46.7%–49.9% | #29–70 | ||
| 32 | gpt-5.1-2025-11-13 | OpenAI | Nov 2025 | $1.25 / $10 | 48.0% | 46.4%–49.6% | #45–242 | ||
| 33 | qwen3.8-max-0902 | Alibaba | Oct 2026 | $2 / $6 | 47.3% | 45.7%–48.9% | #23–155 | ||
| 34 | claude-opus-4-6 | Anthropic | Sep 2026 | $5 / $25 | 47.0% | 45.4%–48.6% | #2–25 | ||
| 35 | deepseek-v4-pro | DeepSeek | Aug 2026 | $0.66 / $1.98 | 47.0% | 45.4%–48.6% | #17–54 |
Showing SimpleQA Verified exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.