Noometry

Model comparison

Grok 4.5 vs Jamba Large

Grok 4.5 has enough public results to be ranked (#25); Jamba Large does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Grok 4.5 xAI

55.0

Rank #25 Confirmed

Jamba Large AI21 Labs

33.1

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. Grok 4.5 scores higher in 2 categories and Jamba Large in 0 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.5 leads 56.1 to 18.0.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 83.5% for Grok 4.5 and 26.1% for Jamba Large.
  • Grok 4.5 is cheaper at $2 / $6 per million input/output tokens, against $2 / $8 for Jamba Large.
  • Grok 4.5 accepts more context: 500K tokens versus 256K.
  • Jamba Large has downloadable open weights; the other is API-only.

Side by side

Grok 4.5Jamba Large
ProviderxAIAI21 Labs
Noometry Index55.033.1
Released2026-07-082025-07-01
WeightsProprietaryOpen
Context window500K256K
Max output500K4K
Input $ / M tokens$2$2
Output $ / M tokens$6$8
Results tracked522

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Grok 4.5: 52.2 (#35), Jamba Large: —

BenchmarkGrok 4.5Jamba Large
DeepSWE53.8%—
FrontierCode42.4%—
LMArena WebDev1553—
SciCode54.1%—
WeirdML46.4%—
LMArena Coding1474—
ALE-Bench1,309—

Agentic & Tool Use Not comparable

Grok 4.5: 44.4 (#17), Jamba Large: —

BenchmarkGrok 4.5Jamba Large
APEX-Agents56.2%—
τ²-bench Banking47.9%—
PostTrainBench23.4%—
GBAEval65.4%—
GDP.pdf14%—
LMArena Search1213—
Vending-Bench 23,887—

Reasoning Grok 4.5 leads

Grok 4.5: 56.1 (#25), Jamba Large: 18.0

BenchmarkGrok 4.5Jamba Large
Kagi LLM Benchmark83.5%26.1%
ARC-AGI-252.6%—
SimpleBench70%—
NYT Connections (extended)79.9%—
ARC-AGI-187.2%—
CritPt15.4%—
Chess Puzzles36%—
LMArena Hard Prompts1462—
DTBench96.5%—
LMCA45.2%—
Surface Evolver Bench74.4%—
Epoch Capabilities Index153.92—

Math Not comparable

Grok 4.5: 60.9 (#35), Jamba Large: —

BenchmarkGrok 4.5Jamba Large
FrontierMath (Tiers 1-3)57.2%—
FrontierMath Tier 424.4%—
OTIS Mock AIME 2024-202597.8%—
ProofBench31%—
LMArena Math1459—

Knowledge Grok 4.5 leads

Grok 4.5: 62.3 (#24), Jamba Large: 37.7

BenchmarkGrok 4.5Jamba Large
GPQA Diamond93.4%—
SimpleQA Verified48.3%—
Vectara Hallucination Rate—9.7%
LMArena Expert1466—

Multimodal Not comparable

Grok 4.5: 37.6 (#72), Jamba Large: —

BenchmarkGrok 4.5Jamba Large
LMArena Vision1288—
Blueprint-Bench 227.3%—
Furniture Assembly22.5%—
LMArena Document1452—

Multilingual Not comparable

Grok 4.5: 54.4 (#42), Jamba Large: —

BenchmarkGrok 4.5Jamba Large
LMArena Non-English1440—
LMArena Chinese1496—
LMArena French1456—
LMArena German1446—
LMArena Japanese1428—
LMArena Korean1404—
LMArena Russian1448—
LMArena Spanish1450—

Instruction Following Not comparable

Grok 4.5: 76.0 (#48), Jamba Large: —

BenchmarkGrok 4.5Jamba Large
LMArena Instruction Following1446—

Long Context Not comparable

Grok 4.5: 44.8 (#56), Jamba Large: —

BenchmarkGrok 4.5Jamba Large
LMArena Longer Query1463—

Writing & Preference Not comparable

Grok 4.5: 65.8 (#42), Jamba Large: —

BenchmarkGrok 4.5Jamba Large
LMArena Text1448—
LMArena Creative Writing1442—
EQ-Bench Creative Writing1579—
LMArena Multi-Turn1456—

Frequently asked questions

Is Grok 4.5 better than Jamba Large?

Grok 4.5 has enough public results to be ranked (#25); Jamba Large does not yet, so treat this comparison as directional.

Which is cheaper, Grok 4.5 or Jamba Large?

Grok 4.5 is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Jamba Large lists at $2 and $8.

Which has the bigger context window?

Grok 4.5 does, with 500K tokens against 256K.

How many benchmarks do Grok 4.5 and Jamba Large share?

1 benchmark has published results for both models. Grok 4.5 has 52 scored results on Noometry and Jamba Large has 2.

Related comparisons

Go deeper