Gemini 4 Carbon added, Claude Fable 5 up to #8 (29 Oct 2026)

BenchLeader refreshed 1636 models from 24 of 24 data feeds (benchmark publishers, aggregators and price lists). 1 new model, 2 top-10 rank changes, 148 price changes, 56 new or updated benchmark results across 24 data feeds.

New models

Gemini 4 Carbon (Google) is now listed; no independent results yet. (details)

Movement in the top 10

Claude Fable 5 moved from #9 to #8 in the BenchLeader Index. (details)
Claude Opus 5.5 (xhigh) moved from #8 to #9 in the BenchLeader Index. (details)

Price changes

Gemini 4 Argon (high) input price moved from $2.00/M to $4.00/M (100% up). (details)
Gemini 4 Argon (high) output price moved from $10.00/M to $20.00/M (100% up). (details)
Gemini 4 Argon (high) cost per task moved from $3.84/M to $7.68/M (100% up). (details)
Qwen3.7 (max) cached input price moved from $0.50/M to $0.33/M (34% down). (details)
GLM 5.2 (max) cached input price moved from $0.26/M to $0.30/M (15% up). (details)
GLM-5 (thinking) cached input price moved from $0.20/M to $0.15/M (25% down). (details)
Qwen3.6 Plus cached input price moved from $0.050/M to $0.028/M (45% down). (details)
Qwen3.8 Max (max) cached input price moved from $0.25/M to $0.22/M (11% down). (details)
Qwen3.7 Plus cached input price moved from $0.080/M to $0.055/M (31% down). (details)
GLM 5.3 (max) cached input price moved from $0.26/M to $0.30/M (15% up). (details)
Qwen3.5 Plus (thinking) input price moved from $0.40/M to $0.12/M (71% down). (details)
Qwen3.5 Plus (thinking) output price moved from $2.40/M to $0.69/M (71% down). (details)
GLM 5.3 Flash cached input price moved from $0.030/M to $0.034/M (15% up). (details)
GLM 5.1 input price moved from $1.40/M to $0.90/M (36% down). (details)
GLM 5.1 output price moved from $4.40/M to $3.59/M (19% down). (details)
GLM 5.1 cached input price moved from $0.26/M to $0.19/M (25% down). (details)
GLM 5V Turbo input price moved from $1.20/M to $0.75/M (38% down). (details)
GLM 5V Turbo output price moved from $4.00/M to $3.29/M (18% down). (details)
GLM 5V Turbo cached input price moved from $0.24/M to $0.18/M (25% down). (details)
GLM-5 input price moved from $1.00/M to $0.60/M (40% down). (details)
GLM-5 output price moved from $3.20/M to $2.69/M (16% down). (details)
GLM-5 cached input price moved from $0.20/M to $0.15/M (25% down). (details)
GLM 5.3 Flash (max) cached input price moved from $0.030/M to $0.034/M (15% up). (details)
Qwen3.5 Flash input price moved from $0.10/M to $0.029/M (71% down). (details)
Qwen3.5 Flash output price moved from $0.40/M to $0.29/M (28% down). (details)
GLM 4.7 input price moved from $0.60/M to $0.45/M (25% down). (details)
GLM 4.7 cached input price moved from $0.11/M to $0.090/M (19% down). (details)
GLM 5.2 input price moved from $1.40/M to $1.20/M (15% down). (details)
GLM 5.2 cached input price moved from $0.26/M to $0.30/M (15% up). (details)
Qwen3 32B input price moved from $0.70/M to $0.29/M (59% down). (details)
…and 118 more.

New benchmark results

SciCode: 8 new results, including GPT-6.1 Terra, Kimi K3.1 Pro, GPT-6.1 Terra… (board)
Startrise Frontend: 8 new results, including Muse Wonder, Gemini 4 Argon, Kimi K3.1 Pro… (board)
MirrorCode: 5 new results, including Gemini 3.7 Flash, Grok 4.6, GPT-5… (board)
APEX-Agents: 4 new results, including GPT-6.1 Terra, Muse Wonder, DeepSeek V4.1 Flash 1017… (board)
ALE-Bench: 4 new results, including GPT-6.1 Terra, DeepSeek V4.1 Flash 1017, Claude Haiku 5.5… (board)
CursorBench: 3 new results, including DeepSeek V4.1 Flash 1017, DeepSeek V4.1 Flash 1017, DeepSeek V4.1 Flash 1017 (board)
ProofBench: 2 new results, including Kimi K3.1 Pro, Beam 1.0 (board)
Remote Labor Index: 1 new result, including Gemini 4 Argon (board)
EQ-Bench 4: 1 new result, including GPT-6.1 Sol (board)
CritPt v2 hard subset (AA): 1 new result, including GLM 5.3 Flash (board)
ARC-AGI-3: 1 new result, including Muse Spark Open (board)

Score revisions

Claude Opus 5 on EQ-Bench 4: 1360 → 1365. (details)
Claude Fable 5.1 (high) on SciCode: 57.6% → 58.7%. (details)
Muse Spark 1.1 on EQ-Bench 4: 1252 → 1244. (details)
Claude Fable 5.1 (medium) on SciCode: 55.3% → 56.4%. (details)
DeepSeek V4.1 Flash 1017 (max) on OpenRouter token share: 19.8% → 21.1%. (details)
Claude Fable 5.1 (low) on SciCode: 55.7% → 56.7%. (details)
GLM 5.3 Flash on OpenRouter token share: 7.5% → 8%. (details)
GLM 5.3 Flash (max) on OpenRouter token share: 7.5% → 8%. (details)
MiniMax M3.1 Flash on OpenRouter token share: 5.9% → 3.5%. (details)
Mistral Medium 3.5 on EQ-Bench 4: 988 → 983. (details)
DeepSeek V4.1 Flash 1017 on OpenRouter token share: 19.8% → 21.1%. (details)
DeepSeek V4.1 Flash 1017 (no reasoning) on OpenRouter token share: 19.8% → 21.1%. (details)
DeepSeek V4.1 Flash 1017 (low) on OpenRouter token share: 19.8% → 21.1%. (details)
DeepSeek V4.1 Flash 1017 (high) on OpenRouter token share: 19.8% → 21.1%. (details)
GLM 5.3 Flash (low) on OpenRouter token share: 7.5% → 8%. (details)
GLM 5.3 Flash (high) on OpenRouter token share: 7.5% → 8%. (details)
GLM 5.3 Flash (no reasoning) on OpenRouter token share: 7.5% → 8%. (details)
DeepSeek V4.1 Flash 1017 (xhigh) on OpenRouter token share: 19.8% → 21.1%. (details)

Speed changes

GPT-6 Astra time to first token changed from 4.91 s to 3.00 s. (details)
GPT-6.1 Terra time to first answer changed from 77.96 s to 189.33 s. (details)
GPT-6.1 Terra response time changed from 83.46 s to 194.83 s. (details)
Claude Fable 5.1 time to first answer changed from 16.85 s to 10.21 s. (details)
Kimi K2.6 output speed changed from 80 tok/s to 51 tok/s. (details)
Kimi K2.6 time to first answer changed from 58.30 s to 89.66 s. (details)
Kimi K2.6 response time changed from 64.55 s to 99.43 s. (details)
Kimi K2.6 thinking time changed from 55.67 s to 86.95 s. (details)
Claude Sonnet 5 time to first answer changed from 6.69 s to 4.07 s. (details)
MiniMax-M2.1 output speed changed from 57 tok/s to 33 tok/s. (details)
MiniMax-M2.1 time to first answer changed from 37.03 s to 62.08 s. (details)
MiniMax-M2.1 response time changed from 45.84 s to 77.15 s. (details)
MiniMax-M2.1 thinking time changed from 35.24 s to 60.30 s. (details)
Beam 1.0 501B A23B output speed changed from 87 tok/s to 121 tok/s. (details)
GPT-5.4 Nano time to first answer changed from 6.05 s to 3.66 s. (details)
…and 9 more.

Today's top five

More: New AI model releases this week, and the full LLM leaderboard 2026.

This digest is generated automatically from the day's data changes. Every line links to the page where you can check the numbers and their source.