Gemini 4 Argon added
The newest model in the AIM LLM Index is Gemini 4 Argon.
AIM LLM Index
v1.10One transparent index combining public benchmarks with AIMultiple's own agentic, RAG and enterprise-reasoning evaluations. How the Index Is Built
TOP MODEL
Claude Opus 5.5
Index 78
Best value
GPT-6.1 Sol
$4.00 / 1M
Fastest model
DeepSeek V4 Flash 0731
0.34s TTFT
Cost vs Performance
Blended cost against LLM Index
AIM LLM Index
Leaderboard
The highest-scoring models across all benchmarks.
Filter & Sort
# | Model | Index | AIM-Agentic-RAG | AIM-AI-Bias | AIM-FinanceReasoning | AIM-Text-to-SQL | CritPt | FrontierMath | MMMU-Pro | SciCode | Terminal-Bench 4.0 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |  Claude Opus 5.5 Anthropic | 78 | 90 | 94 | 92 | 88 | 32 | 95 | 88 | 67 | 60 |
| 2 |  GPT-6 Astra OpenAI | 74 | 84 | 98 | 87 | 66 | 32 | 98 | 87 | 56 | 60 |
| 3 | GPT-6.1 Sol OpenAI | 74 | 81 | 98 | 90 | 65 | 32 | 100 | 86 | 56 | 56 |
| 4 | Claude Sonnet 5.5 Anthropic | 74 | 85 | 93 | 89 | 74 | 31 | 80 | 86 | 61 | 64 |
| 5 | Claude Fable 5.1 Anthropic | 74 | 84 | 98 | 90 | 67 | 31 | 88 | 86 | 63 | 55 |
| 6 |  Gemini 4 Argon Google | 73 | 94 | 98 | 91 | 79 | 27 | 78 | - | 62 | 57 |
| 7 | GPT-6 Sol OpenAI | 70 | 82 | 96 | 89 | 54 | 31 | 90 | 83 | 58 | 44 |
| 8 | Claude Opus 5 Anthropic | 68 | 85 | 82 | 90 | 64 | 29 | 73 | 84 | 56 | 49 |
| 9 |  Muse Wonder Meta | 68 | 86 | 95 | 92 | 56 | 28 | 71 | - | 60 | 52 |
| 10 | Muse Spark 1.3 Meta | 62 | 77 | 96 | 89 | 49 | 26 | 46 | 82 | 60 | 33 |
Page 1 of 3
Cost$8.00
Latency1.84s
Context1M
TTFT1.84s
AIM-Agentic-RAG
90
AIM-AI-Bias
94
AIM-FinanceReasoning
92
AIM-Text-to-SQL
88
CritPt
32
FrontierMath
95
MMMU-Pro
88
SciCode
67
Terminal-Bench 4.0
60
Cost$20.00
Latency6.73s
Context524k
TTFT6.73s
AIM-Agentic-RAG
84
AIM-AI-Bias
98
AIM-FinanceReasoning
87
AIM-Text-to-SQL
66
CritPt
32
FrontierMath
98
MMMU-Pro
87
SciCode
56
Terminal-Bench 4.0
60
Cost$4.00
Latency3.29s
Context1M
TTFT3.29s
AIM-Agentic-RAG
81
AIM-AI-Bias
98
AIM-FinanceReasoning
90
AIM-Text-to-SQL
65
CritPt
32
FrontierMath
100
MMMU-Pro
86
SciCode
56
Terminal-Bench 4.0
56
Cost$4.00
Latency1.25s
Context1M
TTFT1.25s
AIM-Agentic-RAG
85
AIM-AI-Bias
93
AIM-FinanceReasoning
89
AIM-Text-to-SQL
74
CritPt
31
FrontierMath
80
MMMU-Pro
86
SciCode
61
Terminal-Bench 4.0
64
Cost$20.00
Latency2.12s
Context1M
TTFT2.12s
AIM-Agentic-RAG
84
AIM-AI-Bias
98
AIM-FinanceReasoning
90
AIM-Text-to-SQL
67
CritPt
31
FrontierMath
88
MMMU-Pro
86
SciCode
63
Terminal-Bench 4.0
55
Cost$4.00
Latency4.28s
Context1M
TTFT4.28s
AIM-Agentic-RAG
94
AIM-AI-Bias
98
AIM-FinanceReasoning
91
AIM-Text-to-SQL
79
CritPt
27
FrontierMath
78
SciCode
62
Terminal-Bench 4.0
57
Cost$4.00
Latency3.30s
Context1M
TTFT3.30s
AIM-Agentic-RAG
82
AIM-AI-Bias
96
AIM-FinanceReasoning
89
AIM-Text-to-SQL
54
CritPt
31
FrontierMath
90
MMMU-Pro
83
SciCode
58
Terminal-Bench 4.0
44
Cost$10.00
Latency1.93s
Context1M
TTFT1.93s
AIM-Agentic-RAG
85
AIM-AI-Bias
82
AIM-FinanceReasoning
90
AIM-Text-to-SQL
64
CritPt
29
FrontierMath
73
MMMU-Pro
84
SciCode
56
Terminal-Bench 4.0
49
Cost$8.00
Latency50.93s
Context1M
TTFT50.93s
AIM-Agentic-RAG
86
AIM-AI-Bias
95
AIM-FinanceReasoning
92
AIM-Text-to-SQL
56
CritPt
28
FrontierMath
71
SciCode
60
Terminal-Bench 4.0
52
Cost$2.00
Latency68.37s
Context1M
TTFT68.37s
AIM-Agentic-RAG
77
AIM-AI-Bias
96
AIM-FinanceReasoning
89
AIM-Text-to-SQL
49
CritPt
26
FrontierMath
46
MMMU-Pro
82
SciCode
60
Terminal-Bench 4.0
33
Page 1 of 3
Frontier Over Time
LLM Index by model release date
Model × Benchmark
Top models on selected benchmarks
How the Index Is Built
A model's index score is the average of its results across the benchmarks below. Scores already on a 0-100 scale are used as-is; others are rescaled to 0-100. A model missing a benchmark has it excluded rather than scored as zero, and every benchmark carries equal weight. A model needs to be scored in at least 2 AIMultiple benchmarks to be ranked. MMMU-Pro results come from 2 separate sources.
Benchmarks We Used
AIMultiple
AIM-Agentic-RAGMulti-database routing & SQL query generation across 5 databases (BIRD-SQL, 500 questions).AIMultiple
AIM-AI-BiasMultiple-choice bias evaluation: 64 questions across 12 bias categories, each asked 5 times in two runs (v1 and v2), across 109 models. The score is the share of answers that pick the unbiased option, averaged over the two runs.AIMultiple
AIM-FinanceReasoningComplex multi-step financial reasoning across 238 hard FinanceReasoning questions.AIMultiple
AIM-Text-to-SQLNatural-language-to-SQL query generation accuracy across 35+ LLMs.Public
CritPtResearch-level physics problems requiring multi-step derivation.Public
FrontierMathUnpublished, expert-authored research math problems (Tiers 1–4).Public
MMMU-ProCollege-level multimodal understanding across disciplines, hardened against text-only shortcuts.Public
SciCodeResearch-level scientific coding across physics, math, biology & chemistry (338 subproblems)Public
Terminal-Bench 4.0The current Terminal-Bench generation: agentic terminal tasks scored by resolution rate.Changelog
57 updates- v1.10
Added 125 models to the dataset: Claude 3 Haiku, Claude Opus 4.7 (max), Command A, DeepSeek R1 (Jan), DeepSeek R1 0528 Qwen3 8B and 120 more.
- v1.10
Muse Wonder entered the AIM LLM Index.
- v1.10
Added Muse Wonder to the dataset.
- v1.10
Gemini 4 Argon entered the AIM LLM Index.
- v1.10
Added Gemini 4 Argon to the dataset.
- v1.10
MMMU-Pro was added to the index calculation. Version updated to v1.10.
- v1.9
Claude Haiku 5.5 entered the AIM LLM Index.
- v1.9
Added Claude Haiku 5.5 to the dataset.
- v1.9
AIM LLM Index: A model now also needs close to the average number of external benchmark results to be ranked. Version updated to v1.9.
- v1.8
Added 14 models to the dataset: Claude Sonnet 4.6 (max), DeepSeek V4 Flash (Max), DeepSeek V4 Pro (Max), Gemma 4 31B, GPT-5.4 mini (xhigh) and 9 more.
LLM Release TimelineThe pace of AI innovation
AI Labs
DeepSeek V4 Flash Vision Exp
21 AugDeepSeek V4.1 Flash
10 SepDeepSeek V4.1 Flash 1017
17 OctMuse Spark 1.2 Contributor
21 AugMuse Spark 1.3 +1 moreMuse Spark 1.3Muse Spark 1.3 Contributor
02 SepMuse Wonder
12 OctMuse Spark Open
15 OctGemini 3.8 Flash
02 SepNano Banana 2.1
06 OctGemini 4 Argon
13 OctClaude Fable 5.1
01 SepClaude Opus 5.5
22 SepClaude Sonnet 5.5
28 SepClaude Haiku 5.5
07 OctGPT-6 Astra
04 SepGPT-6 Luna +1 moreGPT-6 LunaGPT-6 Sol
22 SepGPT-6.1 Sol
29 Sep
Solar Mini 4
23 SepSolar Decide
28 Sep
Qwen3.8 Flash
26 AugQwen3.8 Max (0902)
03 SepQwen3.8 Omni Flash
21 SepQwen3.8 Max Prime
23 Sep
GLM 5.3 Flash
26 AugGLM 5.3 FlashX
18 SepGLM 5.3 Prime
23 Sep
Grok 4.7
21 Sep
MiMo-V2.6-Flash +2 moreMiMo-V2.6-FlashMiMo-V2.6-ProMiMo-V2.6-Pro-UltraSpeed
21 SepExplore LLM Use Cases, Analyses & Benchmarks
- LLMInsightSep 1
LLM Fine-Tuning Guide for Enterprises
Follow the links for the specific solutions to your LLM output challenges. If your LLM: The widespread adoption of large language models (LLMs) has improved our ability to process human language. However, their generic training often results in suboptimal performance for specific tasks. To overcome this limitation, fine-tuning methods are employed to tailor LLMs to…
- LLMInsightAug 27
LLM Automation: Top 7 Tools & 8 Case Studies
LLM automation refers to shift to intelligent automation tools that leverage LLMs, including AI agents, fine-tuned LLMs and RAG models to automate and coordinate tasks. Explore what LLM automation is, its top real-life applications and major tools: Large language models in automation is a systematic approach that combines Natural Language Processing (NLP) with existing process…
- LLMInsightAug 19
ChatGPT for Customer Service: Top 10 Use Cases
ChatGPT has moved from novelty to infrastructure in customer service. Companies are using it to cut response times, handle volume their teams can’t absorb, and reduce the cost of routine interactions. But results vary sharply depending on how it’s implemented. OpenAI launched GPT-5.6, a materially more capable model that is better at instruction-following, reasoning across…
- LLMBenchmarkAug 16
Intelligence Density of 71 LLMs for Smarter & Denser Models
We tracked 71 LLMs released between February 2023 and May 2026 and collected 10 public benchmarks to measure intelligence density. We divided the capability score by the resource the model consumes (active parameters, training compute, and inference price). To calculate intelligence density, we executed the following steps: See methodology for the scoring approach, and per-resource…
- LLMBenchmarkApr 15
LLM Quantization: BF16 vs FP8 vs INT4
We benchmarked Qwen3-32B at 4 precision levels (BF16, FP8, GPTQ-Int8, GPTQ-Int4) on a single NVIDIA H100 80GB GPU. Each configuration was evaluated on 2 benchmarks (~12.2K questions) covering knowledge and code generation, plus 2,000+ inference runs to measure throughput. Int4 is 2.7x faster than BF16 while losing less than 2 points on MMLU-Pro, but code…
Filters