Google, open weights
Gemma 4 26B A4B IT
Gemma 4 26B A4B IT by Google ranks 92nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.5. Its strongest category is multimodal, where it ranks 46th. API pricing starts at $0.0675 per million input tokens and $0.23 per million output tokens, with a 262K-token context window.
Last verified
Specifications
- Noometry rank
- #92 of 354
- Index score
- 43.5
- Evidence
- Confirmed 28 results
- Provider
Google- Released
- April 2, 2026
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 262K
- Max output
- 33K
- Input price
- $0.0675 / M
- Output price
- $0.23 / M
- Blended price
- $0.11 / M
- Output speed
- Not measured
- Value
- #12 of 219
- Knowledge cutoff
- Unknown
- Input
- text, image
- Hugging Face
- google/gemma-4-26B-A4B-it
Category scores
Each category score combines every public result we have in that category.
- Coding 39.0
- Reasoning 21.8
- Math 47.6
- Knowledge 45.7
- Multimodal 40.6
- Multilingual 53.1
- Instruction Following 74.8
- Long Context 43.6
- Writing & Preference 58.6
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 39.0 | #164 | 4 |
| Reasoning | 21.8 | #213 | 5 |
| Math | 47.6 | #67 | 2 |
| Knowledge | 45.7 | #85 | 3 |
| Multimodal | 40.6 | #46 | 1 |
| Multilingual | 53.1 | #71 | 1 |
| Instruction Following | 74.8 | #82 | 1 |
| Long Context | 43.6 | #91 | 1 |
| Writing & Preference | 58.6 | #115 | 4 |
Strengths and weaknesses
Categories where Gemma 4 26B A4B IT places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Math | 47.6 | +11.0 | #67 of 327, top 21% |
| Multilingual | 53.1 | +5.7 | #71 of 297, top 24% |
| Instruction Following | 74.8 | +3.6 | #82 of 305, top 27% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Reasoning | 21.8 | −1.8 | #213 of 350, top 61% |
| Coding | 39.0 | +0.3 | #164 of 340, top 49% |
| Writing & Preference | 58.6 | +4.8 | #115 of 312, top 37% |
Closest competitors
The models ranked just above and below Gemma 4 26B A4B IT. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| MiMo-V2-Omni | #88 | 43.6 | $0.18 | — | Compare |
| Kimi K2.5 Instant | #89 | 43.6 | — | — | Compare |
| Gemma 4 31B IT | #90 | 43.5 | $0.15 | 3 | Compare |
| Qwen3 235B-A22B | #91 | 43.5 | $1.22 | 85 | Compare |
| MiMo-V2.5 | #93 | 43.4 | $0.18 | — | Compare |
| Kimi K2.7 Code | #94 | 43.3 | $1.71 | — | Compare |
| Qwen3-VL 235B-A22B | #95 | 43.2 | $1.22 | — | Compare |
| Seed 2.0 Pro | #96 | 43.2 | $1.13 | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena WebDev | 1359 | #85 of 113, top 76% | LMArena | 2026-10-08 | |
| SciCode | 40% | #80 of 121, top 67% | Epoch AI | ||
| WeirdML | 35.2% | #92 of 119, top 78% | Epoch AI | ||
| LMArena Coding | 1447 | #92 of 294, top 32% | LMArena | 2026-10-08 | |
| ALE-Bench | 927.17 | #47 of 105, top 45% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| CritPt | 0% | #109 of 134, top 82% | Epoch AI | ||
| Chess Puzzles | 6% | #88 of 129, top 69% | minimal | Epoch AI | 2026-08-06 |
| LMArena Hard Prompts | 1439 | #83 of 297, top 28% | LMArena | 2026-10-08 | |
| DTBench | 74.9% | #87 of 151, top 58% | Epoch AI | ||
| LMCA | 29.7% | #73 of 125, top 59% | Epoch AI | ||
| Epoch Capabilities Index | 141.85 | #101 of 213, top 48% | Epoch AI | 2026-04-02 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 82.2% | #77 of 173, top 45% | minimal | Epoch AI | 2026-08-28 |
| LMArena Math | 1470 | #39 of 285, top 14% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 73.2% | #95 of 186, top 52% | minimal | Epoch AI | 2026-08-06 |
| Vectara Hallucination Rate (lower is better) | 5.2% | #11 of 96, top 12% | Vectara Hallucination Leaderboard | ||
| LMArena Expert | 1447 | #72 of 273, top 27% | LMArena | 2026-10-08 |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Vision | 1260 | #47 of 122, top 39% | LMArena | 2026-10-09 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1421 | #71 of 297, top 24% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1495 | #51 of 285, top 18% | LMArena | 2026-10-08 | |
| LMArena French | 1460 | #51 of 223, top 23% | LMArena | 2026-10-08 | |
| LMArena Russian | 1434 | #63 of 283, top 23% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1417 | #95 of 226, top 43% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1420 | #72 of 298, top 25% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1428 | #82 of 291, top 29% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1434 | #74 of 297, top 25% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1402 | #76 of 295, top 26% | LMArena | 2026-10-08 | |
| EQ-Bench Creative Writing | 1305 | #78 of 115, top 68% | EQ-Bench | ||
| LMArena Multi-Turn | 1441 | #71 of 295, top 25% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| bedrock | $0.13 | $0.40 | — | 2026-10-10 |
| deepinfra | $0.07 | $0.34 | — | 2026-10-10 |
| openrouter | $0.0675 | $0.23 | $0.0375 | 2026-10-10 |
| vertex | $0.15 | $0.60 | $0.015 | 2026-10-10 |
Compare Gemma 4 26B A4B IT
- Gemma 4 26B A4B IT vs Qwen3 235B-A22B
- Gemma 4 26B A4B IT vs MiMo-V2.5
- Gemma 4 26B A4B IT vs Gemma 4 31B IT
- Gemma 4 26B A4B IT vs Kimi K2.7 Code
- Gemma 4 26B A4B IT vs Kimi K2.5 Instant
- Gemma 4 26B A4B IT vs Qwen3-VL 235B-A22B
- Gemma 4 26B A4B IT vs GPT-6 Astra
- Gemma 4 26B A4B IT vs Claude Fable 5.1
- Gemma 4 26B A4B IT vs Kimi K3
- Gemma 4 26B A4B IT vs Grok 4.6
- Gemma 4 26B A4B IT vs Qwen3.8 Max
- Gemma 4 26B A4B IT vs GLM-5.3
- Gemma 4 26B A4B IT vs Muse Spark 1.3
- Gemma 4 26B A4B IT vs DeepSeek V4 Pro
Other Google models
Frequently asked questions
How good is Gemma 4 26B A4B IT?
Gemma 4 26B A4B IT by Google ranks 92nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.5. Its strongest category is multimodal, where it ranks 46th. API pricing starts at $0.0675 per million input tokens and $0.23 per million output tokens, with a 262K-token context window.
How much does Gemma 4 26B A4B IT cost?
Gemma 4 26B A4B IT costs $0.0675 per million input tokens and $0.23 per million output tokens on openrouter, with cached input at $0.0375.
What is Gemma 4 26B A4B IT's context window?
Gemma 4 26B A4B IT accepts up to 262K tokens of input and can write up to 33K tokens in one response.
Is Gemma 4 26B A4B IT open source?
Yes. Gemma 4 26B A4B IT's weights are downloadable from Hugging Face (google/gemma-4-26B-A4B-it); check the license for commercial terms.
What are Gemma 4 26B A4B IT's strengths and weaknesses?
Relative to other ranked models, Gemma 4 26B A4B IT places best in math, multilingual, instruction following and lowest in reasoning, coding, writing & preference.
What is Gemma 4 26B A4B IT best at?
Its best category is multimodal, where it ranks 46th on Noometry.