Allen Institute for AI · Model profile
Tulu3 405B
Intelligence, Performance & Price Analysis
Source: Canonical slug: tulu3-405b · Canonical model registry at build time
Routing verdict
Budget-friendly / task-specific model
Best for high-volume, simple, or domain-specific tasks where cost or speed matters more than deep reasoning.
Tulu3 405B summary metrics
- Intelligence
- 8 scoreLlama 3.1 Tulu3 405B scores 8 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 17).
- Input Price
- Not published
- Output Price
- Not published
Assessment
Routing verdict and task fit
| Workload | Rating | Notes |
|---|---|---|
| Complex reasoning & agentic workflows | Suboptimal | Intelligence score 8 is better suited for straightforward tasks than multi-step reasoning. |
Evidence
Evidence charts
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- GPT-5.5 (xhigh)54.8
- GLM-5.2 (max)51.1
- Gemini 3.5 Flash50.2
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- Muse Spark43.1
- Nemotron 3 Ultra37.8
- Grok 4.3 (high)37.6
- MiMo-V2-Flash24.7
- gpt-oss-120b (high)23.8
- Mistral Large 315.9
- DeepSeek V3 032415.4
- Llama 4 Maverick14.3
- DeepSeek V3 (Dec)14.2
- Tulu3 405B (this model)8.3
| Model | Artificial Analysis Intelligence Index by Open Weights / Proprietary |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| GPT-5.5 (xhigh) | 54.8 |
| GLM-5.2 (max) | 51.1 |
| Gemini 3.5 Flash | 50.2 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| Muse Spark | 43.1 |
| Nemotron 3 Ultra | 37.8 |
| Grok 4.3 (high) | 37.6 |
| MiMo-V2-Flash | 24.7 |
| gpt-oss-120b (high) | 23.8 |
| Mistral Large 3 | 15.9 |
| DeepSeek V3 0324 | 15.4 |
| Llama 4 Maverick | 14.3 |
| DeepSeek V3 (Dec) | 14.2 |
| Tulu3 405B (this model) | 8.3 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- GPT-5.5 (xhigh)54.8
- GLM-5.2 (max)51.1
- Gemini 3.5 Flash50.2
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- Muse Spark43.1
- Nemotron 3 Ultra37.8
- Grok 4.3 (high)37.6
- MiMo-V2-Flash24.7
- gpt-oss-120b (high)23.8
- Mistral Large 315.9
- DeepSeek V3 032415.4
- Llama 4 Maverick14.3
- DeepSeek V3 (Dec)14.2
- Tulu3 405B (this model)8.3
| Model | Artificial Analysis Intelligence Index |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| GPT-5.5 (xhigh) | 54.8 |
| GLM-5.2 (max) | 51.1 |
| Gemini 3.5 Flash | 50.2 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| Muse Spark | 43.1 |
| Nemotron 3 Ultra | 37.8 |
| Grok 4.3 (high) | 37.6 |
| MiMo-V2-Flash | 24.7 |
| gpt-oss-120b (high) | 23.8 |
| Mistral Large 3 | 15.9 |
| DeepSeek V3 0324 | 15.4 |
| Llama 4 Maverick | 14.3 |
| DeepSeek V3 (Dec) | 14.2 |
| Tulu3 405B (this model) | 8.3 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Openness Index: Score
Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open) · Evaluation results measured independently by Artificial Analysis
- Nemotron 3 Ultra83.3
- MiMo-V2-Flash52.8
- DeepSeek V4 Pro (max)50
- GLM-5.2 (max)44.4
- gpt-oss-120b (high)38.9
- Mistral Large 338.9
- Kimi K2.633.3
- MiniMax-M333.3
- Llama 4 Maverick27.8
| Model | Artificial Analysis Openness Index: Score |
|---|---|
| Nemotron 3 Ultra | 83.3 |
| MiMo-V2-Flash | 52.8 |
| DeepSeek V4 Pro (max) | 50 |
| GLM-5.2 (max) | 44.4 |
| gpt-oss-120b (high) | 38.9 |
| Mistral Large 3 | 38.9 |
| Kimi K2.6 | 33.3 |
| MiniMax-M3 | 33.3 |
| Llama 4 Maverick | 27.8 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Chart interpretation
- Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- GPT-5.5 (xhigh)54.8
- GLM-5.2 (max)51.1
- Gemini 3.5 Flash50.2
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- Muse Spark43.1
- Nemotron 3 Ultra37.8
- Grok 4.3 (high)37.6
- gpt-oss-120b (high)23.8
- Tulu3 405B (this model)8.3
| Model | Intelligence |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| GPT-5.5 (xhigh) | 54.8 |
| GLM-5.2 (max) | 51.1 |
| Gemini 3.5 Flash | 50.2 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| Muse Spark | 43.1 |
| Nemotron 3 Ultra | 37.8 |
| Grok 4.3 (high) | 37.6 |
| gpt-oss-120b (high) | 23.8 |
| Tulu3 405B (this model) | 8.3 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
- gpt-oss-120b (high)314 t/s
- Nemotron 3 Ultra250 t/s
- GLM-5.2 (max)218 t/s
- Gemini 3.5 Flash192 t/s
- Grok 4.3 (high)164 t/s
- MiniMax-M399 t/s
- GPT-5.5 (xhigh)88 t/s
- Kimi K2.676 t/s
- DeepSeek V4 Pro (max)72 t/s
- Claude Fable 5 (with fallback)71 t/s
| Model | Speed |
|---|---|
| gpt-oss-120b (high) | 314 t/s |
| Nemotron 3 Ultra | 250 t/s |
| GLM-5.2 (max) | 218 t/s |
| Gemini 3.5 Flash | 192 t/s |
| Grok 4.3 (high) | 164 t/s |
| MiniMax-M3 | 99 t/s |
| GPT-5.5 (xhigh) | 88 t/s |
| Kimi K2.6 | 76 t/s |
| DeepSeek V4 Pro (max) | 72 t/s |
| Claude Fable 5 (with fallback) | 71 t/s |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Output speed context
- Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
Context Window
Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis
- Gemini 3.5 Flash1M
- Claude Fable 5 (with fallback)1M
- GLM-5.2 (max)1M
- DeepSeek V4 Pro (max)1M
- Grok 4.3 (high)1M
- MiniMax-M31M
- Llama 4 Maverick1M
- GPT-5.5 (xhigh)922k
- Nemotron 3 Ultra262.1k
- Muse Spark262.1k
- Kimi K2.6256k
- MiMo-V2-Flash256k
- Mistral Large 3256k
- gpt-oss-120b (high)131.1k
- Tulu3 405B (this model)128k
- DeepSeek V3 0324128k
- DeepSeek V3 (Dec)128k
| Model | Context Window |
|---|---|
| Gemini 3.5 Flash | 1M |
| Claude Fable 5 (with fallback) | 1M |
| GLM-5.2 (max) | 1M |
| DeepSeek V4 Pro (max) | 1M |
| Grok 4.3 (high) | 1M |
| MiniMax-M3 | 1M |
| Llama 4 Maverick | 1M |
| GPT-5.5 (xhigh) | 922k |
| Nemotron 3 Ultra | 262.1k |
| Muse Spark | 262.1k |
| Kimi K2.6 | 256k |
| MiMo-V2-Flash | 256k |
| Mistral Large 3 | 256k |
| gpt-oss-120b (high) | 131.1k |
| Tulu3 405B (this model) | 128k |
| DeepSeek V3 0324 | 128k |
| DeepSeek V3 (Dec) | 128k |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Context window sizing
- Larger context windows enable complex multi-turn tasks but may increase latency and cost for long inputs.
Cost per Intelligence Index Task
Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis
- DeepSeek V3 (Dec)0.00202
- Llama 4 Maverick0.00178
- DeepSeek V4 Pro (max)0.0063
- Mistral Large 30.00455
- gpt-oss-120b (high)0.00454
- MiniMax-M30.0139
- Grok 4.3 (high)0.0101
- DeepSeek V3 03240.00334
- Nemotron 3 Ultra0.0209
- Kimi K2.60.0216
- MiMo-V2-Flash0.00812
- GLM-5.2 (max)0.0268
- Gemini 3.5 Flash0.0884
- GPT-5.5 (xhigh)0.107
- Claude Fable 5 (with fallback)0.367
| Model | Cost per Intelligence Index Task |
|---|---|
| DeepSeek V3 (Dec) | 0.00202 |
| Llama 4 Maverick | 0.00178 |
| DeepSeek V4 Pro (max) | 0.0063 |
| Mistral Large 3 | 0.00455 |
| gpt-oss-120b (high) | 0.00454 |
| MiniMax-M3 | 0.0139 |
| Grok 4.3 (high) | 0.0101 |
| DeepSeek V3 0324 | 0.00334 |
| Nemotron 3 Ultra | 0.0209 |
| Kimi K2.6 | 0.0216 |
| MiMo-V2-Flash | 0.00812 |
| GLM-5.2 (max) | 0.0268 |
| Gemini 3.5 Flash | 0.0884 |
| GPT-5.5 (xhigh) | 0.107 |
| Claude Fable 5 (with fallback) | 0.367 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost per Task
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
- DeepSeek V4 Pro (max)$0.045
- gpt-oss-120b (high)$0.061
- MiniMax-M3$0.125
- Grok 4.3 (high)$0.139
- Nemotron 3 Ultra$0.244
- Kimi K2.6$0.346
- GLM-5.2 (max)$0.370
- Gemini 3.5 Flash$0.586
- GPT-5.5 (xhigh)$0.863
- Claude Fable 5 (with fallback)$2.75
| Model | Cost per Task |
|---|---|
| DeepSeek V4 Pro (max) | $0.045 |
| gpt-oss-120b (high) | $0.061 |
| MiniMax-M3 | $0.125 |
| Grok 4.3 (high) | $0.139 |
| Nemotron 3 Ultra | $0.244 |
| Kimi K2.6 | $0.346 |
| GLM-5.2 (max) | $0.370 |
| Gemini 3.5 Flash | $0.586 |
| GPT-5.5 (xhigh) | $0.863 |
| Claude Fable 5 (with fallback) | $2.75 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost to Run Artificial Analysis Intelligence Index
Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
- DeepSeek V3 (Dec)2.9
- Llama 4 Maverick4
- Mistral Large 38.4
- gpt-oss-120b (high)3.5
- DeepSeek V3 03245.7
- DeepSeek V4 Pro (max)7.2
- MiniMax-M314.5
- Grok 4.3 (high)12.5
- MiMo-V2-Flash11.4
- Nemotron 3 Ultra33.5
- GLM-5.2 (max)32.9
- Kimi K2.625
- Gemini 3.5 Flash114
- GPT-5.5 (xhigh)131.8
- Claude Fable 5 (with fallback)507.6
| Model | Cost to Run Artificial Analysis Intelligence Index |
|---|---|
| DeepSeek V3 (Dec) | 2.9 |
| Llama 4 Maverick | 4 |
| Mistral Large 3 | 8.4 |
| gpt-oss-120b (high) | 3.5 |
| DeepSeek V3 0324 | 5.7 |
| DeepSeek V4 Pro (max) | 7.2 |
| MiniMax-M3 | 14.5 |
| Grok 4.3 (high) | 12.5 |
| MiMo-V2-Flash | 11.4 |
| Nemotron 3 Ultra | 33.5 |
| GLM-5.2 (max) | 32.9 |
| Kimi K2.6 | 25 |
| Gemini 3.5 Flash | 114 |
| GPT-5.5 (xhigh) | 131.8 |
| Claude Fable 5 (with fallback) | 507.6 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Pricing: Cache Hit, Input, and Output
Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis
- Input
- Output
- Cache Hit
- MiMo-V2-Flash$0.400
- gpt-oss-120b (high)$0.900
- Llama 4 Maverick$1.47
- DeepSeek V3 (Dec)$1.29
- DeepSeek V4 Pro (max)$1.31
- MiniMax-M3$1.56
- Mistral Large 3$2.00
- DeepSeek V3 0324$3.64
- Nemotron 3 Ultra$3.60
- Grok 4.3 (high)$3.95
- Kimi K2.6$5.11
- GLM-5.2 (max)$6.06
- Gemini 3.5 Flash$10.65
- GPT-5.5 (xhigh)$35.50
- Claude Fable 5 (with fallback)$61.00
| Model | Input | Output | Cache Hit | Total |
|---|---|---|---|---|
| MiMo-V2-Flash | $0.100 | $0.300 | Not published | $0.400 |
| gpt-oss-120b (high) | $0.150 | $0.600 | $0.150 | $0.900 |
| Llama 4 Maverick | $0.350 | $0.850 | $0.270 | $1.47 |
| DeepSeek V3 (Dec) | $0.400 | $0.890 | Not published | $1.29 |
| DeepSeek V4 Pro (max) | $0.435 | $0.870 | $0.0036 | $1.31 |
| MiniMax-M3 | $0.300 | $1.20 | $0.060 | $1.56 |
| Mistral Large 3 | $0.500 | $1.50 | Not published | $2.00 |
| DeepSeek V3 0324 | $1.19 | $1.25 | $1.19 | $3.64 |
| Nemotron 3 Ultra | $0.675 | $2.67 | $0.250 | $3.60 |
| Grok 4.3 (high) | $1.25 | $2.50 | $0.200 | $3.95 |
| Kimi K2.6 | $0.950 | $4.00 | $0.160 | $5.11 |
| GLM-5.2 (max) | $1.40 | $4.40 | $0.260 | $6.06 |
| Gemini 3.5 Flash | $1.50 | $9.00 | $0.150 | $10.65 |
| GPT-5.5 (xhigh) | $5.00 | $30.00 | $0.500 | $35.50 |
| Claude Fable 5 (with fallback) | $10.00 | $50.00 | $1.00 | $61.00 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Chart interpretation
- Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.
Model Size: Total and Active Parameters
Comparison between total model parameters and parameters active during inference · Evaluation results measured independently by Artificial Analysis
- Passive Params
- Active Params
- DeepSeek V4 Pro (max)1,600B
- Kimi K2.61,000B
- GLM-5.2 (max)753B
- Mistral Large 3675B
- DeepSeek V3 0324671B
- DeepSeek V3 (Dec)671B
- Nemotron 3 Ultra550B
- MiniMax-M3428B
- Tulu3 405B (this model)405B
- Llama 4 Maverick402B
- MiMo-V2-Flash309B
- gpt-oss-120b (high)117B
| Model | Passive Params | Active Params | Total |
|---|---|---|---|
| DeepSeek V4 Pro (max) | 1,551B | 49B | 1,600B |
| Kimi K2.6 | 968B | 32B | 1,000B |
| GLM-5.2 (max) | 713B | 40B | 753B |
| Mistral Large 3 | 634B | 41B | 675B |
| DeepSeek V3 0324 | 634B | 37B | 671B |
| DeepSeek V3 (Dec) | 634B | 37B | 671B |
| Nemotron 3 Ultra | 495B | 55B | 550B |
| MiniMax-M3 | 405B | 23B | 428B |
| Tulu3 405B (this model) | 0B | 405B | 405B |
| Llama 4 Maverick | 385B | 17B | 402B |
| MiMo-V2-Flash | 294B | 15B | 309B |
| gpt-oss-120b (high) | 111.9B | 5.1B | 117B |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Architecture scale
- Larger models generally perform better but cost more to serve. Active parameter count matters for inference efficiency.
Specifications
Architecture and limits
| Specification | Value | Source |
|---|---|---|
| Model type | Open weights | faq |
| Reasoning | No | faq |
| Input modalities | Llama 3.1 Tulu3 405B supports text input. | faq |
| Output modalities | Llama 3.1 Tulu3 405B supports text output. | faq |
| Context window | 130k tokens | faq |
| Open weights / source | Yes, Llama 3.1 Tulu3 405B is open weights. The model weights are publicly available and can be downloaded for self-hosting. | faq |
| Parameters | Llama 3.1 Tulu3 405B has 405 billion parameters. | faq |
| License | Llama 3.1 Tulu3 405B is released under the LLAMA 3.1 COMMUNITY LICENSE AGREEMENT license. This license allows commercial use. | faq |
Method
Methodology & Provenance
This page is rendered from the normalized profile and page JSON for Tulu3 405B.
Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.
Questions
Model FAQ and technical disclosures
Models
Related
- 01Allen Institute for AIOther Allen Institute for AI models in the catalog.
- 02LeaderboardsCertified metric ranks, when published.