Skip to content

Benchmarks

Sources
8
Entries tracked
22,308
Last sync
4 min
All sources syncing normally
  • Arena · Text10 hours ago
  • Arena · WebDev10 hours ago
  • Arena · Vision10 hours ago
  • Arena · Agent10 hours ago
  • GPQA Diamond4 minutes ago
  • SWE-bench4 minutes ago
  • Terminal-Bench4 minutes ago
  • ARC-AGI-24 minutes ago
French ×1278 of 278 models
ModelOrg± CISwingAdd to compare
1Muse Spark 1.3 (Max)metaSep 2026$1.25 / $4.251,5281,502–1,555#13–33
2Claude Fable 5 (High)anthropicSep 2026$10 / $501,5221,505–1,539#4–20
3Muse Spark 1.2 (xHigh)metaOct 2026$1.25 / $4.251,5211,485–1,558#13–112
4Muse SparkmetaSep 2026—1,5201,492–1,548#16–40
5Claude Fable 5.1 (Max)anthropicSep 2026$10 / $501,5171,489–1,545#2–21
6Claude Opus 4.7 (High)anthropicSep 2026$5 / $251,5171,503–1,531#1–18
7glm-5.3-maxzaiAug 2026$0.08 / $1.801,5161,493–1,539#18–52
8Muse Spark 1.1metaSep 2026$1.25 / $4.251,5141,497–1,531#21–115
9gpt-6.1-sol-maxopenaiOct 2026$2 / $101,5131,475–1,552#1–15
10gemini-3.6-flash-highgoogleSep 2026$0.75 / $3.751,5121,493–1,531#16–95
11Claude Opus 4.6 (High)anthropicSep 2026$5 / $251,5101,497–1,524#2–25
12gpt-5.6-sol-xhighopenaiSep 2026$4 / $201,5091,491–1,527#6–25
13Gemini 3.7 Flash (High)googleOct 2026$0.75 / $3.751,5091,487–1,530#9–57
14claude-opus-4-8-highanthropicSep 2026$5 / $251,5071,493–1,522#15–33
15Kimi K3 (Max)moonshotJun 2026$0.30 / $11.941,5071,489–1,525#10–39
16Claude Opus 5 (High)anthropicSep 2026$5 / $251,5071,492–1,522#5–11
17claude-sonnet-5.5-xhighanthropicOct 2026$2 / $101,5071,471–1,542#4–26
18qwen3.8-maxalibabaOct 2026$2 / $61,5061,486–1,526#12–40
19Gemini 3 ProgoogleJan 2026—1,5061,486–1,526#23–90
20grok-4.20-beta-0309-reasoningxaiSep 2026—1,5031,488–1,517#49–207
21Claude Opus 5.5 (High)anthropicOct 2026$4 / $201,5021,466–1,537#2–11
22Gemini 3.1 Pro PreviewgoogleSep 2026$2 / $121,5011,489–1,512#9–36
23gpt-5.4-highopenaiSep 2026$2.50 / $151,5001,486–1,514#12–29
24glm-5.3-flashzaiAug 2026$0.05 / $0.201,5001,481–1,518#26–60
25gpt-5.5openaiSep 2026$5 / $301,5001,486–1,513#9–34
26grok-4.7-xhighxaiOct 2026$2 / $61,4981,466–1,529#21–72
27Gemini 3.8 Flash (High)googleOct 2026$0.83 / $4.131,4961,478–1,515#2–29
28grok-4.20-beta1xaiOct 2026—1,4941,473–1,516#46–119
29mistral-large-4mistralOct 2026—1,4941,457–1,530#51–349
30gemini-3.5-flash-highgoogleSep 2026$1.50 / $91,4931,476–1,510#10–26
31gpt-5.5-instantopenaiSep 2026—1,4921,472–1,512#52–114
32gemini-3-flashgoogleJan 2026—1,4921,471–1,514#38–153
33gpt-5.6-terra-xhighopenaiSep 2026$2 / $121,4921,475–1,510#13–59
34glm-5.2-maxzaiJun 2026$0.62 / $2.421,4921,477–1,507#9–49
35grok-4.20-multi-agent-beta-0309xaiOct 2026—1,4911,477–1,505#48–86

Showing French exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.

The few things in AI and quantum that actually mattered this week — honestly summarised.

One email a week. Unsubscribe in one click. No tracking, no sharing.